Qwen3-Coder-30B-A3B-Instruct-GGUF
codingtool-callinghot
lemonade-server pull Qwen3-Coder-30B-A3B-Instruct-GGUFModels
Browse models and install them with the pull command. You can also register any Hugging Face model into your Lemonade Server with the advanced pull command options.
Showing
All labels
All recipes
148 models
Hot models
Recommended models. Full supported catalog is listed below.
Qwen3-Coder-Next-GGUF
codingtool-callinghot
lemonade-server pull Qwen3-Coder-Next-GGUFGemma-4-26B-A4B-it-GGUF
hottool-callingvisionllamacpp
lemonade-server pull Gemma-4-26B-A4B-it-GGUFGemma-4-31B-it-GGUF
hottool-callingvisionllamacpp
lemonade-server pull Gemma-4-31B-it-GGUFQwen3.5-4B-GGUF
visiontool-callinghot
lemonade-server pull Qwen3.5-4B-GGUFQwen3.5-35B-A3B-GGUF
visiontool-callinghot
lemonade-server pull Qwen3.5-35B-A3B-GGUFQwen3-0.6B-GGUF
reasoning
lemonade-server pull Qwen3-0.6B-GGUF| Checkpoint | unsloth/Qwen3-0.6B-GGUF |
| GGUF Variant | Q4_0 |
| Recipe | llamacpp |
| Size (GB) | 0.38 |
Qwen3-1.7B-GGUF
reasoning
lemonade-server pull Qwen3-1.7B-GGUF| Checkpoint | unsloth/Qwen3-1.7B-GGUF |
| GGUF Variant | Q4_0 |
| Recipe | llamacpp |
| Size (GB) | 1.06 |
Qwen3-4B-GGUF
reasoning
lemonade-server pull Qwen3-4B-GGUF| Checkpoint | unsloth/Qwen3-4B-GGUF |
| GGUF Variant | Q4_0 |
| Recipe | llamacpp |
| Size (GB) | 2.38 |
Qwen3-8B-GGUF
reasoning
lemonade-server pull Qwen3-8B-GGUF| Checkpoint | unsloth/Qwen3-8B-GGUF |
| GGUF Variant | Q4_1 |
| Recipe | llamacpp |
| Size (GB) | 5.25 |
DeepSeek-Qwen3-8B-GGUF
reasoning
lemonade-server pull DeepSeek-Qwen3-8B-GGUF| Checkpoint | unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF |
| GGUF Variant | Q4_1 |
| Recipe | llamacpp |
| Size (GB) | 5.25 |
Qwen3-14B-GGUF
reasoning
lemonade-server pull Qwen3-14B-GGUF| Checkpoint | unsloth/Qwen3-14B-GGUF |
| GGUF Variant | Q4_0 |
| Recipe | llamacpp |
| Size (GB) | 8.54 |
Qwen3-4B-Instruct-2507-GGUF
tool-calling
lemonade-server pull Qwen3-4B-Instruct-2507-GGUF| Checkpoint | unsloth/Qwen3-4B-Instruct-2507-GGUF |
| GGUF Variant | Qwen3-4B-Instruct-2507-Q4_K_M.gguf |
| Recipe | llamacpp |
| Size (GB) | 2.5 |
Qwen3-30B-A3B-GGUF
reasoning
lemonade-server pull Qwen3-30B-A3B-GGUF| Checkpoint | unsloth/Qwen3-30B-A3B-GGUF |
| GGUF Variant | Q4_0 |
| Recipe | llamacpp |
| Size (GB) | 17.4 |
Qwen3-30B-A3B-Instruct-2507-GGUF
tool-calling
lemonade-server pull Qwen3-30B-A3B-Instruct-2507-GGUF| Checkpoint | unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF |
| GGUF Variant | Qwen3-30B-A3B-Instruct-2507-Q4_0.gguf |
| Recipe | llamacpp |
| Size (GB) | 17.4 |
Qwen3-Coder-30B-A3B-Instruct-GGUF
codingtool-callinghot
lemonade-server pull Qwen3-Coder-30B-A3B-Instruct-GGUF| Checkpoint | unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF |
| GGUF Variant | Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf |
| Recipe | llamacpp |
| Size (GB) | 18.6 |
Qwen3-Coder-Next-GGUF
codingtool-callinghot
lemonade-server pull Qwen3-Coder-Next-GGUF| Checkpoint | unsloth/Qwen3-Coder-Next-GGUF |
| GGUF Variant | Qwen3-Coder-Next-MXFP4_MOE.gguf |
| Recipe | llamacpp |
| Size (GB) | 43.7 |
Nemotron-3-Nano-30B-A3B-GGUF
lemonade-server pull Nemotron-3-Nano-30B-A3B-GGUF| Checkpoint | unsloth/Nemotron-3-Nano-30B-A3B-GGUF |
| GGUF Variant | Nemotron-3-Nano-30B-A3B-UD-Q4_K_XL.gguf |
| Recipe | llamacpp |
| Size (GB) | 22.8 |
Gemma-3-4b-it-GGUF
vision
lemonade-server pull Gemma-3-4b-it-GGUF| Checkpoint | ggml-org/gemma-3-4b-it-GGUF |
| GGUF Variant | Q4_K_M |
| Mmproj | mmproj-model-f16.gguf |
| Recipe | llamacpp |
| Size (GB) | 3.61 |
Gemma-4-26B-A4B-it-GGUF
hottool-callingvisionllamacpp
lemonade-server pull Gemma-4-26B-A4B-it-GGUF| Checkpoint | unsloth/gemma-4-26B-A4B-it-GGUF |
| GGUF Variant | UD-Q4_K_M |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 16.9 |
Gemma-4-31B-it-GGUF
hottool-callingvisionllamacpp
lemonade-server pull Gemma-4-31B-it-GGUF| Checkpoint | unsloth/gemma-4-31B-it-GGUF |
| GGUF Variant | Q4_K_M |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 18.3 |
Gemma-4-E4B-it-GGUF
tool-callingvisionllamacpp
lemonade-server pull Gemma-4-E4B-it-GGUF| Checkpoint | unsloth/gemma-4-E4B-it-GGUF |
| GGUF Variant | Q4_K_M |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 5 |
Gemma-4-E2B-it-GGUF
tool-callingvisionllamacpp
lemonade-server pull Gemma-4-E2B-it-GGUF| Checkpoint | unsloth/gemma-4-E2B-it-GGUF |
| GGUF Variant | Q4_K_M |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 3.1 |
Phi-4-mini-instruct-GGUF
lemonade-server pull Phi-4-mini-instruct-GGUF| Checkpoint | unsloth/Phi-4-mini-instruct-GGUF |
| GGUF Variant | Phi-4-mini-instruct-Q4_K_M.gguf |
| Recipe | llamacpp |
| Size (GB) | 2.49 |
LFM2-1.2B-GGUF
lemonade-server pull LFM2-1.2B-GGUF| Checkpoint | LiquidAI/LFM2-1.2B-GGUF |
| GGUF Variant | LFM2-1.2B-Q4_K_M.gguf |
| Recipe | llamacpp |
| Size (GB) | 0.731 |
LFM2.5-1.2B-Instruct-GGUF
lemonade-server pull LFM2.5-1.2B-Instruct-GGUF| Checkpoint | LiquidAI/LFM2.5-1.2B-Instruct-GGUF |
| GGUF Variant | LFM2.5-1.2B-Instruct-Q4_K_M.gguf |
| Recipe | llamacpp |
| Size (GB) | 0.731 |
Jan-nano-128k-GGUF
lemonade-server pull Jan-nano-128k-GGUF| Checkpoint | Menlo/Jan-nano-128k-gguf |
| GGUF Variant | jan-nano-128k-Q4_K_M.gguf |
| Recipe | llamacpp |
| Size (GB) | 2.5 |
Jan-v1-4B-GGUF
lemonade-server pull Jan-v1-4B-GGUF| Checkpoint | janhq/Jan-v1-4B-GGUF |
| GGUF Variant | Jan-v1-4B-Q4_K_M.gguf |
| Recipe | llamacpp |
| Size (GB) | 2.5 |
Llama-3.2-1B-Instruct-GGUF
lemonade-server pull Llama-3.2-1B-Instruct-GGUF| Checkpoint | unsloth/Llama-3.2-1B-Instruct-GGUF |
| GGUF Variant | Llama-3.2-1B-Instruct-UD-Q4_K_XL.gguf |
| Recipe | llamacpp |
| Size (GB) | 0.834 |
Llama-3.2-3B-Instruct-GGUF
lemonade-server pull Llama-3.2-3B-Instruct-GGUF| Checkpoint | unsloth/Llama-3.2-3B-Instruct-GGUF |
| GGUF Variant | Llama-3.2-3B-Instruct-UD-Q4_K_XL.gguf |
| Recipe | llamacpp |
| Size (GB) | 2.06 |
SmolLM3-3B-GGUF
lemonade-server pull SmolLM3-3B-GGUF| Checkpoint | unsloth/SmolLM3-3B-128K-GGUF |
| GGUF Variant | SmolLM3-3B-128K-UD-Q4_K_XL.gguf |
| Recipe | llamacpp |
| Size (GB) | 1.94 |
Ministral-3-3B-Instruct-2512-GGUF
vision
lemonade-server pull Ministral-3-3B-Instruct-2512-GGUF| Checkpoint | mistralai/Ministral-3-3B-Instruct-2512-GGUF |
| GGUF Variant | Ministral-3-3B-Instruct-2512-Q4_K_M.gguf |
| Mmproj | Ministral-3-3B-Instruct-2512-BF16-mmproj.gguf |
| Recipe | llamacpp |
| Size (GB) | 2.85 |
Qwen2.5-VL-7B-Instruct-GGUF
vision
lemonade-server pull Qwen2.5-VL-7B-Instruct-GGUF| Checkpoint | ggml-org/Qwen2.5-VL-7B-Instruct-GGUF |
| GGUF Variant | Q4_K_M |
| Mmproj | mmproj-Qwen2.5-VL-7B-Instruct-f16.gguf |
| Recipe | llamacpp |
| Size (GB) | 4.68 |
Qwen2.5-VL-3B-Instruct-GGUF
vision
lemonade-server pull Qwen2.5-VL-3B-Instruct-GGUF| Checkpoint | ggml-org/Qwen2.5-VL-3B-Instruct-GGUF |
| GGUF Variant | Q4_K_M |
| Mmproj | mmproj-Qwen2.5-VL-3B-Instruct-f16.gguf |
| Recipe | llamacpp |
| Size (GB) | 3.27 |
Qwen3-VL-4B-Instruct-GGUF
vision
lemonade-server pull Qwen3-VL-4B-Instruct-GGUF| Checkpoint | Qwen/Qwen3-VL-4B-Instruct-GGUF |
| GGUF Variant | Q4_K_M |
| Mmproj | mmproj-Qwen3VL-4B-Instruct-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 3.33 |
Qwen3-VL-8B-Instruct-GGUF
vision
lemonade-server pull Qwen3-VL-8B-Instruct-GGUF| Checkpoint | Qwen/Qwen3-VL-8B-Instruct-GGUF |
| GGUF Variant | Q4_K_M |
| Mmproj | mmproj-Qwen3VL-8B-Instruct-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 6.19 |
Qwen3-Next-80B-A3B-Instruct-GGUF
tool-calling
lemonade-server pull Qwen3-Next-80B-A3B-Instruct-GGUF| Checkpoint | unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF |
| GGUF Variant | Qwen3-Next-80B-A3B-Instruct-UD-Q4_K_XL.gguf |
| Recipe | llamacpp |
| Size (GB) | 45.1 |
Qwen3.5-0.8B-GGUF
visiontool-calling
lemonade-server pull Qwen3.5-0.8B-GGUF| Checkpoint | unsloth/Qwen3.5-0.8B-GGUF |
| GGUF Variant | Qwen3.5-0.8B-UD-Q4_K_XL.gguf |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 0.56 |
Qwen3.5-2B-GGUF
visiontool-calling
lemonade-server pull Qwen3.5-2B-GGUF| Checkpoint | unsloth/Qwen3.5-2B-GGUF |
| GGUF Variant | Qwen3.5-2B-UD-Q4_K_XL.gguf |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 1.34 |
Qwen3.5-4B-GGUF
visiontool-callinghot
lemonade-server pull Qwen3.5-4B-GGUF| Checkpoint | unsloth/Qwen3.5-4B-GGUF |
| GGUF Variant | Qwen3.5-4B-UD-Q4_K_XL.gguf |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 2.91 |
Qwen3.5-9B-GGUF
visiontool-calling
lemonade-server pull Qwen3.5-9B-GGUF| Checkpoint | unsloth/Qwen3.5-9B-GGUF |
| GGUF Variant | Qwen3.5-9B-UD-Q4_K_XL.gguf |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 5.97 |
Qwen3.5-35B-A3B-GGUF
visiontool-callinghot
lemonade-server pull Qwen3.5-35B-A3B-GGUF| Checkpoint | unsloth/Qwen3.5-35B-A3B-GGUF |
| GGUF Variant | Qwen3.5-35B-A3B-UD-Q4_K_XL.gguf |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 19.7 |
Qwen3.5-122B-A10B-GGUF
visiontool-callinghot
lemonade-server pull Qwen3.5-122B-A10B-GGUF| Checkpoint | unsloth/Qwen3.5-122B-A10B-GGUF |
| GGUF Variant | UD-Q4_K_XL |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 68.4 |
Qwen3.5-27B-GGUF
visiontool-calling
lemonade-server pull Qwen3.5-27B-GGUF| Checkpoint | unsloth/Qwen3.5-27B-GGUF |
| GGUF Variant | Qwen3.5-27B-UD-Q4_K_XL.gguf |
| Mmproj | mmproj-F16.gguf |
| Recipe | llamacpp |
| Size (GB) | 16.7 |
nomic-embed-text-v1-GGUF
embeddings
lemonade-server pull nomic-embed-text-v1-GGUF| Checkpoint | nomic-ai/nomic-embed-text-v1-GGUF |
| GGUF Variant | Q4_K_S |
| Recipe | llamacpp |
| Size (GB) | 0.0781 |
nomic-embed-text-v2-moe-GGUF
embeddings
lemonade-server pull nomic-embed-text-v2-moe-GGUF| Checkpoint | nomic-ai/nomic-embed-text-v2-moe-GGUF |
| GGUF Variant | Q8_0 |
| Recipe | llamacpp |
| Size (GB) | 0.51 |
Qwen3-Embedding-0.6B-GGUF
embeddings
lemonade-server pull Qwen3-Embedding-0.6B-GGUF| Checkpoint | Qwen/Qwen3-Embedding-0.6B-GGUF |
| GGUF Variant | Qwen3-Embedding-0.6B-Q8_0.gguf |
| Recipe | llamacpp |
| Size (GB) | 0.64 |
Qwen3-Embedding-4B-GGUF
embeddings
lemonade-server pull Qwen3-Embedding-4B-GGUF| Checkpoint | Qwen/Qwen3-Embedding-4B-GGUF |
| GGUF Variant | Qwen3-Embedding-4B-Q8_0.gguf |
| Recipe | llamacpp |
| Size (GB) | 4.28 |
Qwen3-Embedding-8B-GGUF
embeddings
lemonade-server pull Qwen3-Embedding-8B-GGUF| Checkpoint | Qwen/Qwen3-Embedding-8B-GGUF |
| GGUF Variant | Qwen3-Embedding-8B-Q8_0.gguf |
| Recipe | llamacpp |
| Size (GB) | 8.05 |
bge-reranker-v2-m3-GGUF
reranking
lemonade-server pull bge-reranker-v2-m3-GGUF| Checkpoint | pqnet/bge-reranker-v2-m3-Q8_0-GGUF |
| Recipe | llamacpp |
| Size (GB) | 0.53 |
Devstral-Small-2507-GGUF
codingtool-calling
lemonade-server pull Devstral-Small-2507-GGUF| Checkpoint | mistralai/Devstral-Small-2507_gguf |
| GGUF Variant | Q4_K_M |
| Recipe | llamacpp |
| Size (GB) | 14.3 |
Qwen2.5-Coder-32B-Instruct-GGUF
coding
lemonade-server pull Qwen2.5-Coder-32B-Instruct-GGUF| Checkpoint | Qwen/Qwen2.5-Coder-32B-Instruct-GGUF |
| GGUF Variant | Q4_K_M |
| Recipe | llamacpp |
| Size (GB) | 19.85 |
gpt-oss-120b-mxfp-GGUF
hotreasoningtool-calling
lemonade-server pull gpt-oss-120b-mxfp-GGUF| Checkpoint | ggml-org/gpt-oss-120b-GGUF |
| GGUF Variant | * |
| Recipe | llamacpp |
| Size (GB) | 63.3 |
gpt-oss-20b-mxfp4-GGUF
hotreasoningtool-calling
lemonade-server pull gpt-oss-20b-mxfp4-GGUF| Checkpoint | ggml-org/gpt-oss-20b-GGUF |
| Recipe | llamacpp |
| Size (GB) | 12.1 |
GLM-4.5-Air-UD-Q4K-XL-GGUF
reasoning
lemonade-server pull GLM-4.5-Air-UD-Q4K-XL-GGUF| Checkpoint | unsloth/GLM-4.5-Air-GGUF |
| GGUF Variant | UD-Q4_K_XL |
| Recipe | llamacpp |
| Size (GB) | 73.1 |
GLM-4.7-Flash-GGUF
tool-calling
lemonade-server pull GLM-4.7-Flash-GGUF| Checkpoint | unsloth/GLM-4.7-Flash-GGUF |
| GGUF Variant | GLM-4.7-Flash-UD-Q4_K_XL.gguf |
| Recipe | llamacpp |
| Size (GB) | 17.6 |
granite-4.0-h-tiny-GGUF
tool-calling
lemonade-server pull granite-4.0-h-tiny-GGUF| Checkpoint | unsloth/granite-4.0-h-tiny-GGUF |
| GGUF Variant | Q4_K_M |
| Recipe | llamacpp |
| Size (GB) | 4.25 |
LFM2-8B-A1B-GGUF
lemonade-server pull LFM2-8B-A1B-GGUF| Checkpoint | LiquidAI/LFM2-8B-A1B-GGUF |
| GGUF Variant | Q4_K_M |
| Recipe | llamacpp |
| Size (GB) | 4.8 |
LFM2-24B-A2B-GGUF
lemonade-server pull LFM2-24B-A2B-GGUF| Checkpoint | LiquidAI/LFM2-24B-A2B-GGUF |
| GGUF Variant | Q4_K_M |
| Recipe | llamacpp |
| Size (GB) | 14.4 |
Qwen2.5-0.5B-Instruct-CPU
lemonade-server pull Qwen2.5-0.5B-Instruct-CPU| Checkpoint | amd/Qwen2.5-0.5B-Instruct-quantized_int4-float16-cpu-onnx |
| Recipe | ryzenai-llm |
| Size (GB) | 0.77 |
Phi-3-Mini-Instruct-CPU
lemonade-server pull Phi-3-Mini-Instruct-CPU| Checkpoint | amd/Phi-3-mini-4k-instruct_int4_float16_onnx_cpu |
| Recipe | ryzenai-llm |
| Size (GB) | 2.23 |
Qwen-1.5-7B-Chat-CPU
lemonade-server pull Qwen-1.5-7B-Chat-CPU| Checkpoint | amd/Qwen1.5-7B-Chat_uint4_asym_g128_float16_onnx_cpu |
| Recipe | ryzenai-llm |
| Size (GB) | 5.89 |
DeepSeek-R1-Distill-Llama-8B-CPU
reasoning
lemonade-server pull DeepSeek-R1-Distill-Llama-8B-CPU| Checkpoint | amd/DeepSeek-R1-Distill-Llama-8B-awq-asym-uint4-g128-lmhead-onnx-cpu |
| Recipe | ryzenai-llm |
| Size (GB) | 5.78 |
DeepSeek-R1-Distill-Qwen-7B-CPU
reasoning
lemonade-server pull DeepSeek-R1-Distill-Qwen-7B-CPU| Checkpoint | amd/DeepSeek-R1-Distill-Llama-8B-awq-asym-uint4-g128-lmhead-onnx-cpu |
| Recipe | ryzenai-llm |
| Size (GB) | 5.78 |
AMD-OLMo-1B-SFT-DPO-Hybrid
lemonade-server pull AMD-OLMo-1B-SFT-DPO-Hybrid| Checkpoint | amd/AMD-OLMo-1B-SFT-DPO-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 1.38 |
CodeLlama-7b-Instruct-hf-Hybrid
coding
lemonade-server pull CodeLlama-7b-Instruct-hf-Hybrid| Checkpoint | amd/CodeLlama-7b-Instruct-hf-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 6.74 |
DeepSeek-R1-Distill-Llama-8B-Hybrid
reasoning
lemonade-server pull DeepSeek-R1-Distill-Llama-8B-Hybrid| Checkpoint | amd/DeepSeek-R1-Distill-Llama-8B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.47 |
DeepSeek-R1-Distill-Qwen-1.5B-Hybrid
reasoning
lemonade-server pull DeepSeek-R1-Distill-Qwen-1.5B-Hybrid| Checkpoint | amd/DeepSeek-R1-Distill-Qwen-1.5B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 2.04 |
DeepSeek-R1-Distill-Qwen-7B-Hybrid
reasoning
lemonade-server pull DeepSeek-R1-Distill-Qwen-7B-Hybrid| Checkpoint | amd/DeepSeek-R1-Distill-Qwen-7B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.08 |
Llama-2-7b-chat-hf-Hybrid
lemonade-server pull Llama-2-7b-chat-hf-Hybrid| Checkpoint | amd/Llama-2-7b-chat-hf-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 6.8 |
Llama-2-7b-hf-Hybrid
lemonade-server pull Llama-2-7b-hf-Hybrid| Checkpoint | amd/Llama-2-7b-hf-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 6.8 |
Llama-3.1-8B-Hybrid
lemonade-server pull Llama-3.1-8B-Hybrid| Checkpoint | amd/Llama-3.1-8B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.47 |
Llama-3.2-1B-Hybrid
lemonade-server pull Llama-3.2-1B-Hybrid| Checkpoint | amd/Llama-3.2-1B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 1.76 |
Llama-3.2-1B-Instruct-Hybrid
lemonade-server pull Llama-3.2-1B-Instruct-Hybrid| Checkpoint | amd/Llama-3.2-1B-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 1.76 |
Llama-3.2-3B-Hybrid
lemonade-server pull Llama-3.2-3B-Hybrid| Checkpoint | amd/Llama-3.2-3B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 3.98 |
Llama-3.2-3B-Instruct-Hybrid
lemonade-server pull Llama-3.2-3B-Instruct-Hybrid| Checkpoint | amd/Llama-3.2-3B-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 3.98 |
Meta-Llama-3-8B-Hybrid
lemonade-server pull Meta-Llama-3-8B-Hybrid| Checkpoint | amd/Meta-Llama-3-8B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.44 |
Meta-Llama-3.1-8B-Instruct-Hybrid
lemonade-server pull Meta-Llama-3.1-8B-Instruct-Hybrid| Checkpoint | amd/Meta-Llama-3.1-8B-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.47 |
Mistral-7B-Instruct-v0.1-Hybrid
lemonade-server pull Mistral-7B-Instruct-v0.1-Hybrid| Checkpoint | amd/Mistral-7B-Instruct-v0.1-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 7.3 |
Mistral-7B-Instruct-v0.2-Hybrid
lemonade-server pull Mistral-7B-Instruct-v0.2-Hybrid| Checkpoint | amd/Mistral-7B-Instruct-v0.2-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 7.3 |
Mistral-7B-Instruct-v0.3-Hybrid
lemonade-server pull Mistral-7B-Instruct-v0.3-Hybrid| Checkpoint | amd/Mistral-7B-Instruct-v0.3-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 7.31 |
Mistral-7B-v0.3-Hybrid
lemonade-server pull Mistral-7B-v0.3-Hybrid| Checkpoint | amd/Mistral-7B-v0.3-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 7.31 |
Phi-3-mini-128k-instruct-Hybrid
lemonade-server pull Phi-3-mini-128k-instruct-Hybrid| Checkpoint | amd/Phi-3-mini-128k-instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 3.92 |
Phi-3-mini-4k-instruct-Hybrid
lemonade-server pull Phi-3-mini-4k-instruct-Hybrid| Checkpoint | amd/Phi-3-mini-4k-instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 3.9 |
Phi-3.5-mini-instruct-Hybrid
lemonade-server pull Phi-3.5-mini-instruct-Hybrid| Checkpoint | amd/Phi-3.5-mini-instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 3.92 |
Phi-4-mini-instruct-Hybrid
lemonade-server pull Phi-4-mini-instruct-Hybrid| Checkpoint | amd/Phi-4-mini-instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 5.1 |
Phi-4-mini-reasoning-Hybrid
reasoning
lemonade-server pull Phi-4-mini-reasoning-Hybrid| Checkpoint | amd/Phi-4-mini-reasoning-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 5.1 |
Qwen-2.5-1.5B-Instruct-Hybrid
lemonade-server pull Qwen-2.5-1.5B-Instruct-Hybrid| Checkpoint | amd/Qwen-2.5_1.5B_Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 2.02 |
Qwen1.5-7B-Chat-Hybrid
lemonade-server pull Qwen1.5-7B-Chat-Hybrid| Checkpoint | amd/Qwen1.5-7B-Chat-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.23 |
Qwen2-1.5B-Hybrid
lemonade-server pull Qwen2-1.5B-Hybrid| Checkpoint | amd/Qwen2-1.5B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 2.04 |
Qwen2-7B-Hybrid
lemonade-server pull Qwen2-7B-Hybrid| Checkpoint | amd/Qwen2-7B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.08 |
Qwen2.5-0.5B-Instruct-Hybrid
lemonade-server pull Qwen2.5-0.5B-Instruct-Hybrid| Checkpoint | amd/Qwen2.5-0.5B-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 0.77 |
Qwen2.5-14B-instruct-Hybrid
lemonade-server pull Qwen2.5-14B-instruct-Hybrid| Checkpoint | amd/Qwen2.5-14B-instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 15.31 |
Qwen2.5-3B-Instruct-Hybrid
lemonade-server pull Qwen2.5-3B-Instruct-Hybrid| Checkpoint | amd/Qwen2.5_3B_Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 3.7 |
Qwen2.5-7B-Instruct-Hybrid
lemonade-server pull Qwen2.5-7B-Instruct-Hybrid| Checkpoint | amd/Qwen2.5-7B-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.06 |
Qwen2.5-Coder-0.5B-Instruct-Hybrid
coding
lemonade-server pull Qwen2.5-Coder-0.5B-Instruct-Hybrid| Checkpoint | amd/Qwen2.5-Coder-0.5B-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 0.77 |
Qwen2.5-Coder-1.5B-Instruct-Hybrid
coding
lemonade-server pull Qwen2.5-Coder-1.5B-Instruct-Hybrid| Checkpoint | amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 2.02 |
Qwen2.5-Coder-7B-Instruct-Hybrid
coding
lemonade-server pull Qwen2.5-Coder-7B-Instruct-Hybrid| Checkpoint | amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.06 |
Qwen3-1.7B-Hybrid
reasoning
lemonade-server pull Qwen3-1.7B-Hybrid| Checkpoint | amd/Qwen3-1.7B-awq-quant-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 2.38 |
Qwen3-14B-Hybrid
reasoning
lemonade-server pull Qwen3-14B-Hybrid| Checkpoint | amd/Qwen3-14B-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 15.31 |
Qwen3-4B-Hybrid
reasoning
lemonade-server pull Qwen3-4B-Hybrid| Checkpoint | amd/Qwen3-4B-awq-quant-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 4.82 |
Qwen3-8B-Hybrid
reasoning
lemonade-server pull Qwen3-8B-Hybrid| Checkpoint | amd/Qwen3-8B-awq-quant-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 8.77 |
SmolLM-135M-Instruct-Hybrid
lemonade-server pull SmolLM-135M-Instruct-Hybrid| Checkpoint | amd/SmolLM-135M-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 0.22 |
SmolLM2-135M-Instruct-Hybrid
lemonade-server pull SmolLM2-135M-Instruct-Hybrid| Checkpoint | amd/SmolLM2-135M-Instruct-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 0.22 |
chatglm3-6b-Hybrid
lemonade-server pull chatglm3-6b-Hybrid| Checkpoint | amd/chatglm3-6b-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 6.43 |
gemma-2-2b-Hybrid
lemonade-server pull gemma-2-2b-Hybrid| Checkpoint | amd/gemma-2-2b-onnx-ryzenai-1.7-hybrid |
| Recipe | ryzenai-llm |
| Size (GB) | 3.76 |
CodeLlama-7b-Instruct-hf-NPU
coding
lemonade-server pull CodeLlama-7b-Instruct-hf-NPU| Checkpoint | amd/CodeLlama-7b-Instruct-hf-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 7.03 |
DeepSeek-R1-Distill-Llama-8B-NPU
reasoning
lemonade-server pull DeepSeek-R1-Distill-Llama-8B-NPU| Checkpoint | amd/DeepSeek-R1-Distill-Llama-8B-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.66 |
DeepSeek-R1-Distill-Qwen-1.5B-NPU
reasoning
lemonade-server pull DeepSeek-R1-Distill-Qwen-1.5B-NPU| Checkpoint | amd/DeepSeek-R1-Distill-Qwen-1.5B-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 2.14 |
DeepSeek-R1-Distill-Qwen-7B-NPU
reasoning
lemonade-server pull DeepSeek-R1-Distill-Qwen-7B-NPU| Checkpoint | amd/DeepSeek-R1-Distill-Qwen-7B-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.26 |
Gemma-3-4b-it-mm-NPU
vision
lemonade-server pull Gemma-3-4b-it-mm-NPU| Checkpoint | amd/Gemma-3-4b-it-mm-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 6.22 |
Llama-2-7b-chat-hf-NPU
lemonade-server pull Llama-2-7b-chat-hf-NPU| Checkpoint | amd/Llama-2-7b-chat-hf-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 6.95 |
Llama-2-7b-hf-NPU
lemonade-server pull Llama-2-7b-hf-NPU| Checkpoint | amd/Llama-2-7b-hf-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 6.95 |
Llama-3.1-8B-NPU
lemonade-server pull Llama-3.1-8B-NPU| Checkpoint | amd/Llama-3.1-8B-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.66 |
Llama-3.2-1B-Instruct-NPU
lemonade-server pull Llama-3.2-1B-Instruct-NPU| Checkpoint | amd/Llama-3.2-1B-Instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 1.82 |
Llama-3.2-1B-NPU
lemonade-server pull Llama-3.2-1B-NPU| Checkpoint | amd/Llama-3.2-1B-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 1.82 |
Meta-Llama-3-8B-NPU
lemonade-server pull Meta-Llama-3-8B-NPU| Checkpoint | amd/Meta-Llama-3-8B-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.6 |
Meta-Llama-3.1-8B-Instruct-NPU
lemonade-server pull Meta-Llama-3.1-8B-Instruct-NPU| Checkpoint | amd/Meta-Llama-3.1-8B-Instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.66 |
Mistral-7B-Instruct-v0.1-NPU
lemonade-server pull Mistral-7B-Instruct-v0.1-NPU| Checkpoint | amd/Mistral-7B-Instruct-v0.1-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 7.46 |
Mistral-7B-Instruct-v0.2-NPU
lemonade-server pull Mistral-7B-Instruct-v0.2-NPU| Checkpoint | amd/Mistral-7B-Instruct-v0.2-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 7.46 |
Mistral-7B-Instruct-v0.3-NPU
lemonade-server pull Mistral-7B-Instruct-v0.3-NPU| Checkpoint | amd/Mistral-7B-Instruct-v0.3-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 7.54 |
Mistral-7B-v0.3-NPU
lemonade-server pull Mistral-7B-v0.3-NPU| Checkpoint | amd/Mistral-7B-v0.3-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 7.54 |
Phi-3-mini-128k-instruct-NPU
lemonade-server pull Phi-3-mini-128k-instruct-NPU| Checkpoint | amd/Phi-3-mini-128k-instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 4.05 |
Phi-3-mini-4k-instruct-NPU
lemonade-server pull Phi-3-mini-4k-instruct-NPU| Checkpoint | amd/Phi-3-mini-4k-instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 4 |
Phi-3.5-mini-instruct-NPU
lemonade-server pull Phi-3.5-mini-instruct-NPU| Checkpoint | amd/Phi-3.5-mini-instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 4.05 |
Phi-4-mini-instruct-NPU
lemonade-server pull Phi-4-mini-instruct-NPU| Checkpoint | amd/Phi-4-mini-instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 5.21 |
Qwen-2.5-1.5B-Instruct-NPU
lemonade-server pull Qwen-2.5-1.5B-Instruct-NPU| Checkpoint | amd/Qwen-2.5_1.5B_Instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 2.1 |
Qwen1.5-7B-Chat-NPU
lemonade-server pull Qwen1.5-7B-Chat-NPU| Checkpoint | amd/Qwen1.5-7B-Chat-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.4 |
Qwen2-1.5B-NPU
lemonade-server pull Qwen2-1.5B-NPU| Checkpoint | amd/Qwen2-1.5B-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 2.14 |
Qwen2-7B-NPU
lemonade-server pull Qwen2-7B-NPU| Checkpoint | amd/Qwen2-7B-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.27 |
Qwen2.5-3B-Instruct-NPU
lemonade-server pull Qwen2.5-3B-Instruct-NPU| Checkpoint | amd/Qwen2.5-3B-Instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 3.81 |
Qwen2.5-7B-Instruct-NPU
lemonade-server pull Qwen2.5-7B-Instruct-NPU| Checkpoint | amd/Qwen2.5-7B-Instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.22 |
Qwen2.5-Coder-1.5B-Instruct-NPU
coding
lemonade-server pull Qwen2.5-Coder-1.5B-Instruct-NPU| Checkpoint | amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 2.1 |
Qwen2.5-Coder-7B-Instruct-NPU
coding
lemonade-server pull Qwen2.5-Coder-7B-Instruct-NPU| Checkpoint | amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 8.22 |
chatglm3-6b-NPU
lemonade-server pull chatglm3-6b-NPU| Checkpoint | amd/chatglm3-6b-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 6.55 |
gpt-oss-20b-NPU
lemonade-server pull gpt-oss-20b-NPU| Checkpoint | amd/gpt-oss-20b-onnx-ryzenai-npu |
| Recipe | ryzenai-llm |
| Size (GB) | 12.49 |
Whisper-Tiny
audiotranscription
lemonade-server pull Whisper-Tiny| Checkpoints | [object Object] |
| Recipe | whispercpp |
| Size (GB) | 0.075 |
Whisper-Base
audiotranscription
lemonade-server pull Whisper-Base| Checkpoints | [object Object] |
| Recipe | whispercpp |
| Size (GB) | 0.142 |
Whisper-Small
audiotranscription
lemonade-server pull Whisper-Small| Checkpoints | [object Object] |
| Recipe | whispercpp |
| Size (GB) | 0.466 |
Whisper-Medium
audiotranscription
lemonade-server pull Whisper-Medium| Checkpoints | [object Object] |
| Recipe | whispercpp |
| Size (GB) | 1.42 |
Whisper-Large-v3
audiotranscription
lemonade-server pull Whisper-Large-v3| Checkpoints | [object Object] |
| Recipe | whispercpp |
| Size (GB) | 2.87 |
Whisper-Large-v3-Turbo
audiotranscriptionhot
lemonade-server pull Whisper-Large-v3-Turbo| Checkpoints | [object Object] |
| Recipe | whispercpp |
| Size (GB) | 1.55 |
SD-Turbo
image
lemonade-server pull SD-Turbo| Checkpoint | stabilityai/sd-turbo |
| GGUF Variant | sd_turbo.safetensors |
| Recipe | sd-cpp |
| Size (GB) | 5.2 |
| Default Steps | 4 |
| Default CFG Scale | 1 |
| Default Size | 512x512 |
SDXL-Turbo
image
lemonade-server pull SDXL-Turbo| Checkpoint | stabilityai/sdxl-turbo |
| GGUF Variant | sd_xl_turbo_1.0_fp16.safetensors |
| Recipe | sd-cpp |
| Size (GB) | 6.9 |
| Default Steps | 4 |
| Default CFG Scale | 1 |
| Default Size | 512x512 |
SD-1.5
image
lemonade-server pull SD-1.5| Checkpoint | stable-diffusion-v1-5/stable-diffusion-v1-5 |
| GGUF Variant | v1-5-pruned.safetensors |
| Recipe | sd-cpp |
| Size (GB) | 4.3 |
| Default Steps | 20 |
| Default CFG Scale | 7.5 |
| Default Size | 512x512 |
SDXL-Base-1.0
image
lemonade-server pull SDXL-Base-1.0| Checkpoint | stabilityai/stable-diffusion-xl-base-1.0 |
| GGUF Variant | sd_xl_base_1.0.safetensors |
| Recipe | sd-cpp |
| Size (GB) | 6.9 |
| Default Steps | 20 |
| Default CFG Scale | 7.5 |
| Default Size | 1024x1024 |
Flux-2-Klein-4B
imageedit
lemonade-server pull Flux-2-Klein-4B| Checkpoints | [object Object] |
| Recipe | sd-cpp |
| Size (GB) | 16 |
| Default Steps | 4 |
| Default CFG Scale | 1 |
| Default Size | 1024x1024 |
Flux-2-Klein-9B-GGUF
imageedit
lemonade-server pull Flux-2-Klein-9B-GGUF| Checkpoints | [object Object] |
| Recipe | sd-cpp |
| Size (GB) | 18 |
| Default Steps | 4 |
| Default CFG Scale | 1 |
| Default Size | 1024x1024 |
Qwen-Image-GGUF
image
lemonade-server pull Qwen-Image-GGUF| Checkpoints | [object Object] |
| Recipe | sd-cpp |
| Size (GB) | 10 |
| Default Steps | 20 |
| Default CFG Scale | 2.5 |
| Default Size | 512x512 |
| Recipe Options | [object Object] |
Qwen-Image-2512-GGUF
image
lemonade-server pull Qwen-Image-2512-GGUF| Checkpoints | [object Object] |
| Recipe | sd-cpp |
| Size (GB) | 12 |
| Default Steps | 20 |
| Default CFG Scale | 2.5 |
| Default Size | 512x512 |
| Recipe Options | [object Object] |
Z-Image-Turbo
image
lemonade-server pull Z-Image-Turbo| Checkpoints | [object Object] |
| Recipe | sd-cpp |
| Size (GB) | 20 |
| Default Steps | 9 |
| Default CFG Scale | 1 |
| Default Size | 1024x1024 |
RealESRGAN-x4plus
esrganimage
lemonade-server pull RealESRGAN-x4plus| Checkpoint | amd/realesrgan-x4plus |
| GGUF Variant | RealESRGAN_x4plus.pth |
| Recipe | sd-cpp |
| Size (GB) | 0.064 |
RealESRGAN-x4plus-anime
esrganimage
lemonade-server pull RealESRGAN-x4plus-anime| Checkpoint | amd/realesrgan-x4plus-anime-6b |
| GGUF Variant | RealESRGAN_x4plus_anime_6B.pth |
| Recipe | sd-cpp |
| Size (GB) | 0.017 |
kokoro-v1
ttsspeech
lemonade-server pull kokoro-v1| Checkpoint | mikkoph/kokoro-onnx |
| Recipe | kokoro |
| Size (GB) | 0.34 |