unsloth / deepseek-r1 family
deepseek-r1-zero
deepseek/deepseek-r1-zero
Run locally Smallest indexed GGUF / needs Ollama
ollama run hf.co/deepseek/deepseek-r1-zero/DeepSeek-R1-Zero-Q2_K_XS/DeepSeek-R1-Zero-Q2_K_XS-00001-of-00005.gguf Benchmarks
Where it scores.
General Provisional
73.3
Coding Provisional
73.3
Math Provisional
73.3
Reasoning Provisional
73.3
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| Q2_K_XS / smallest | GGUF | 221.3 GB | — | DeepSeek-R1-Zero-Q2_K_XS/DeepSeek-R1-Zero-Q2_K_XS-00001-of-00005.gguf |
| Q2_K_L | GGUF | 244.2 GB | — | DeepSeek-R1-Zero-Q2_K_L/DeepSeek-R1-Zero-Q2_K_L-00001-of-00005.gguf |
| Q3_K_M | GGUF | 319.2 GB | — | DeepSeek-R1-Zero-Q3_K_M/DeepSeek-R1-Zero-Q3_K_M-00001-of-00007.gguf |
| Q4_K_M | GGUF | 404.4 GB | — | DeepSeek-R1-Zero-Q4_K_M/DeepSeek-R1-Zero-Q4_K_M-00001-of-00009.gguf |
| BF16 | GGUF | 713.3 GB | — | DeepSeek-R1-Zero-Q8_0/DeepSeek-R1-Zero-BF16-256x20B-Q8_0-00001-of-00016.gguf |
Sizes are file sizes, not peak runtime memory.
Raw benchmarks
The inputs.
| Source | Task | Raw | Normalized |
|---|---|---|---|
| ZeroEval | GPQA | 73.3 | 73.3 |
From the Hugging Face model card
About this model.
From the Hugging Face model card