Yes — with 12.0 GB to spare
DeepSeek-R1-Distill-Qwen 14B at Q4_K_M fits your A10 entirely on the GPU at 8K context, at an estimated 44 tokens per second. Past 71K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
The 2025 reasoning-per-gigabyte pick for a 12 GB card. Qwen3.5 9B in thinking mode has since overtaken it.
Hardware requirements What hardware do I need to run DeepSeek-R1-Distill-Qwen 14B? →At Q4_K_M with an 8K context: a 16 GB GPU (RTX 5080) or a 24 GB Mac (M4 Pro). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 27.6 GB | 29.7 GB | — | ~3.9 | Reference | 7.3 GB over |
| Q8_0 | 14.6 GB | 16.7 GB | 38K | 25 | −0.1% ppl | Long context |
| Q6_K | 11.3 GB | 13.4 GB | 55K | 32 | −0.4% ppl | Long context |
| Q5_K_M | 9.8 GB | 11.9 GB | 64K | 37 | −0.8% ppl | Long context |
| Q4_K_M | 8.3 GB | 10.4 GB | 71K | 44 | −1.9% ppl | Recommended |
| Q3_K_M | 6.7 GB | 8.8 GB | 80K | 54 | −5.4% ppl | Long context |
| Q2_K | 5.8 GB | 7.9 GB | 85K | 63 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ ollama pull deepseek-r1:14b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run deepseek-r1:14b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on an A10
| Model | Total | Tok/s est. | |
|---|---|---|---|
| DeepSeek-R1-Distill-Qwen 7B 7.62B · same family |
Q4_K_M · 5.3 GB | 85 | Runs great |
| DeepSeek-R1-Distill-Qwen 32B 32.8B · same family |
Q4_K_M · 21.0 GB | 20 | Tight fit |
| DeepSeek-R1-Distill-Llama 70B 70.6B · same family |
Q4_K_M · 42.8 GB | ~1.6 | CPU offload |
| DeepSeek-R1 671B 671B MoE · same family |
Q4_K_M · 378.4 GB | — | Won't fit |
| Qwen3 14B 14.8B · similar size |
Q4_K_M · 10.2 GB | 44 | Runs great |
| Qwen2.5-Coder 14B 14.8B · similar size |
Q4_K_M · 10.4 GB | 44 | Runs great |
| Phi-4 14B 14.7B · similar size |
Q4_K_M · 10.4 GB | 44 | Runs great |
DeepSeek-R1-Distill-Qwen 14B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
10.4 GB | ~7.9 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
10.4 GB | 26 | Tight fit |
| GeForce RTX 5080 14.4 GB usable · 960 GB/s |
10.4 GB | 70 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
10.4 GB | 8.1 | Tight fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
10.4 GB | 73 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
10.4 GB | 70 | Runs great |
| M4 Pro · 24 GB 18.0 GB usable · 273 GB/s |
10.4 GB | 18 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
10.4 GB | 27 | Runs great |