Models / DeepSeek
Can an RTX 3060 12GB run DeepSeek R1 Distill 14B?
14B reasoning distill. A frequent llama.cpp comparison point.
- Stored parameters
- 14B
- Active parameters
- Dense
- Q4 total (estimate)
- 9.2 GB
- License
- MIT (base model license also applies)
Model card. DeepSeek's distill of Qwen2.5 14B. The release is a 14B dense model.
Compatibility
| Hardware | Q4 | Q8 | FP16 |
|---|---|---|---|
| M3 Pro 18GB Apple · 18 GB unified | 15.6 GB Tight estimate No measured run | 28.8 GB Over estimate No measured run | |
| M3 Ultra 512GB Apple · 512 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| 2× NVIDIA GB10 NVIDIA · 256 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M3 Ultra 256GB Apple · 256 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M5 Ultra 256GB Apple · 256 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M2 Ultra 192GB Apple · 192 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| NVIDIA GB10 NVIDIA · 128 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| Ryzen AI Max+ 395 128GB AMD · 128 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M1 Ultra 128GB Apple · 128 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M5 Max 128GB Apple · 128 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| 4× RTX 3090 NVIDIA · 96 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| RTX Pro 6000 Blackwell NVIDIA · 96 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M5 Ultra 96GB Apple · 96 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| Ryzen AI Max+ 395 64GB AMD · 64 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| 2× RTX 3090 NVIDIA · 48 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M4 Pro 48GB Apple · 48 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M4 Max 36GB Apple · 36 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Tight estimate No measured run |
| M5 Max 36GB Apple · 36 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Tight estimate No measured run |
| RTX 5090 NVIDIA · 32 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| Radeon AI Pro R9700 AMD · 32 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| Intel Arc Pro B70 Intel · 32 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run |
| M4 32GB Apple · 32 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Tight estimate No measured run |
| M6 32GB Apple · 32 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Tight estimate No measured run |
| RTX 3090 NVIDIA · 24 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Over estimate No measured run |
| RTX 4090 NVIDIA · 24 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Over estimate No measured run |
| TITAN RTX NVIDIA · 24 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Over estimate No measured run |
| Radeon RX 7900 XTX AMD · 24 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Over estimate No measured run |
| M4 Pro 24GB Apple · 24 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Over estimate No measured run |
| RTX 4060 Ti 16GB NVIDIA · 16 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Tight estimate No measured run | 28.8 GB Over estimate No measured run |
| RTX 5060 Ti 16GB NVIDIA · 16 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Tight estimate No measured run | 28.8 GB Over estimate No measured run |
| RTX 5070 Ti NVIDIA · 16 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Tight estimate No measured run | 28.8 GB Over estimate No measured run |
| M4 16GB Apple · 16 GB unified | 9.2 GB Fits estimate No measured run | 15.6 GB Tight estimate No measured run | 28.8 GB Over estimate No measured run |
| RTX 3060 12GB NVIDIA · 12 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Over estimate No measured run | 28.8 GB Over estimate No measured run |
| RTX 3080 Ti NVIDIA · 12 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Over estimate No measured run | 28.8 GB Over estimate No measured run |
| RTX 4070 Ti NVIDIA · 12 GB VRAM | 9.2 GB Fits estimate No measured run | 15.6 GB Over estimate No measured run | 28.8 GB Over estimate No measured run |
| RTX 2060 Super NVIDIA · 8 GB VRAM | 9.2 GB Over estimate No measured run | 15.6 GB Over estimate No measured run | 28.8 GB Over estimate No measured run |
Measured runs
| Hardware | Quant | tok/s | Runtime | Source |
|---|---|---|---|---|
| RTX 4090 | not stated | 92.49 | llama.cpp | Source · checked · prefill 3685 |
| RTX 3080 Ti | not stated | 70.74 | llama.cpp | Source · checked · prefill 2004 |
| Radeon AI Pro R9700 | not stated | 53.72 | llama.cpp | Source · checked · prefill 846 |
| M3 Ultra 512GB | not stated | 51.85 | llama.cpp | Source · checked · prefill 707 |
| RTX 4070 Ti | not stated | 49.74 | llama.cpp | Source · checked · prefill 1732 |
| M1 Ultra 128GB | not stated | 41.51 | llama.cpp | Source · checked · prefill 473 |
| RTX 3060 12GB | not stated | 29.77 | llama.cpp | Source · checked · prefill 784 |
| M3 Pro 18GB | Q4_K_M (8.99 GB, Ollama tag deepseek-r1:14b) | 14.7 | Ollama 0.40.13 (Metal) | Source · checked |