Yes — with 1.7 GB to spare
DeepSeek-R1-Distill-Qwen 7B at Q4_K_M fits your GeForce RTX 3070 Ti entirely on the GPU at 8K context, at an estimated 86 tokens per second. Past 38K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Reasoning traces on a 7B budget. Expect long outputs — budget context accordingly.
Hardware requirements What hardware do I need to run DeepSeek-R1-Distill-Qwen 7B? →At Q4_K_M with an 8K context: a 8 GB GPU (RTX 4060 Laptop) or a 16 GB Mac (M4). 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 | 14.2 GB | 15.2 GB | — | ~4.1 | Reference | 8.2 GB over |
| Q8_0 | 7.5 GB | 8.6 GB | — | ~17 | −0.1% ppl | 1.6 GB over |
| Q6_K | 5.8 GB | 6.9 GB | 10K | 63 | −0.4% ppl | Fits |
| Q5_K_M | 5.0 GB | 6.1 GB | 25K | 73 | −0.8% ppl | Long context |
| Q4_K_M | 4.3 GB | 5.3 GB | 38K | 86 | −1.9% ppl | Recommended |
| Q3_K_M | 3.5 GB | 4.5 GB | 53K | 106 | −5.4% ppl | Long context |
| Q2_K | 3.0 GB | 4.0 GB | 62K | 124 | −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-r1:7b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run deepseek-r1:7b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on a GeForce RTX 3070 Ti
| Model | Total | Tok/s est. | |
|---|---|---|---|
| DeepSeek-R1-Distill-Qwen 14B 14.8B · same family |
Q4_K_M · 10.4 GB | ~9.3 | CPU offload |
| DeepSeek-R1-Distill-Qwen 32B 32.8B · same family |
Q4_K_M · 21.0 GB | ~2.5 | CPU offload |
| DeepSeek-R1-Distill-Llama 70B 70.6B · same family |
Q4_K_M · 42.8 GB | — | Won't fit |
| DeepSeek-R1 671B 671B MoE · same family |
Q4_K_M · 378.4 GB | — | Won't fit |
| Qwen2.5-Coder 7B 7.62B · similar size |
Q4_K_M · 5.3 GB | 86 | Runs great |
| Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE · similar size |
Q4_K_M · 5.1 GB | 194 | Runs great |
| Olmo 3 7B Instruct 7.3B · similar size |
Q4_K_M · 7.2 GB | ~62 | CPU offload |
DeepSeek-R1-Distill-Qwen 7B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
5.3 GB | 36 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
5.3 GB | 51 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
5.3 GB | 16 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
5.3 GB | 142 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
5.3 GB | 136 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
5.3 GB | 52 | Runs great |