Alptekinege / deepseek-r1 family
DeepSeek-R1-Qwen-Coder-8B
HeraiHench/DeepSeek-R1-Qwen-Coder-8B
Run locally Smallest indexed GGUF / needs Ollama
ollama run hf.co/HeraiHench/DeepSeek-R1-Qwen-Coder-8B/deepseek-r1-qwen-coder-8b-q4_k_m-imat.gguf Benchmarks
Where it scores.
General Provisional —
Coding Provisional —
Math Provisional —
Reasoning Provisional —
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| Q4 / smallest | GGUF | 5.0 GB | — | deepseek-r1-qwen-coder-8b-q4_k_m-imat.gguf |
Sizes are file sizes, not peak runtime memory.
From the Hugging Face model card
About this model.
From the Hugging Face model card