DeepSeek Coder 6.7B
DeepSeek Coder 6.7B is an open-weights language model from DeepSeek, released November 2, 2023. It has 6.7B parameters (dense). On the Epoch Capabilities Index it scores 67.8, rank 250 of 256 rated models.
Check it against your own PC →
Can you run DeepSeek Coder 6.7B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 8 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 5.2 GB | 3.0 GB | ~8 |
| 8 GB VRAM | Runs on GPU | Q4_K_M (very good) | 6.8 GB | – | ~38 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 8.2 GB | – | ~38 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 8.2 GB | – | ~52 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 8.2 GB | – | ~93 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 8.2 GB | – | ~160 |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 15.2% |
Links
Models with a similar score
XGen-7B · Phi-1.5 · Qwen2.5-Coder-0.5B · StarCoder 2 3B · open_llama_7b
More from DeepSeek
DeepSeek V4.1 Flash 1017 · DeepSeek V4 Flash Vision Exp · DeepSeek V4.1 Flash · DeepSeek V4 Pro 0813 · DeepSeek V4 Flash 0731 · DeepSeek V4 Pro DSpark · DeepSeek V4 Flash DSpark · DeepSeek-V4-Pro