§01·model · /models
Qwen2.5 14B
llmactiveApache-2.0
14B instruction-tuned LLM by Alibaba from the Qwen2.5 generation, strong at multilingual work, code and maths — and the base that DeepSeek distilled its R1 14B reasoning model from, which is also catalogued here. The single recipe runs on AMD rather than NVIDIA: a 24 GB Radeon RX 7900 XTX under ROCm, recorded at 32 tokens/s at Q4_K_M. Apache-2.0.
§02·same family
1 other modelOther models grouped with Qwen2.5 14B. Sizes and modalities can differ, and nothing here says whether one fits your GPU — open a model for its own compatibility table.
§03·GPUs that run this model
1 total| GPU | VRAM | Series | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|---|---|
| RX 7900 XTX | 24GB | amd | 32tokens/s | 24GB | ✓ | 1benchrecipe | check ↗ |
✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit