Only with CPU offload
DeepSeek-R1-Distill-Qwen 32B at Q4_K_M needs 21.0 GB but only 14.4 GB is addressable, so about 36% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 4.8 tokens per second — usable for batch work, painful for chat.
MIT-licensed and close to the 70B distill on maths. A 24 GB card handles it at Q4.
Hardware requirements What hardware do I need to run DeepSeek-R1-Distill-Qwen 32B? →At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 36 GB Mac (M4 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
Fits instead: DeepSeek-R1-Distill-Qwen 14B (10.4 GB) · DeepSeek-R1-Distill-Qwen 7B (5.3 GB)
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 32.5 GB | 35.1 GB | — | ~1.7 | −0.1% ppl | 20.7 GB over |
| Q6_K | 25.0 GB | 27.6 GB | — | ~2.6 | −0.4% ppl | 13.2 GB over |
| Q5_K_M | 21.7 GB | 24.3 GB | — | ~3.4 | −0.8% ppl | 9.9 GB over |
| Q4_K_M | 18.4 GB | 21.0 GB | — | ~4.8 | −1.9% ppl | 6.6 GB over |
| Q3_K_M | 14.9 GB | 17.5 GB | — | ~9.1 | −5.4% ppl | 3.1 GB over |
| Q2_K | 12.8 GB | 15.4 GB | 4K | ~20 | −15% ppl | 1.0 GB over |
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
$ llama-server \
-hf deepseek-ai/DeepSeek-R1-Distill-Qwen-32B:Q4_K_M \
-c 8192 -ngl 40
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a CMP 100-210
| Model | Total | Tok/s est. | |
|---|---|---|---|
| DeepSeek-R1-Distill-Llama 70B 70.6B · same family |
Q4_K_M · 42.8 GB | ~1.2 | CPU offload |
| DeepSeek-R1-Distill-Qwen 14B 14.8B · same family |
Q4_K_M · 10.4 GB | 60 | Runs great |
| DeepSeek-R1-Distill-Qwen 7B 7.62B · same family |
Q4_K_M · 5.3 GB | 117 | Runs great |
| DeepSeek-R1 671B 671B MoE · same family |
Q4_K_M · 378.4 GB | — | Won't fit |
| Qwen3 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | ~4.8 | CPU offload |
| Qwen2.5-Coder 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | ~4.8 | CPU offload |
| LLM-jp 4 33B Thinking 33.2B · similar size |
Q4_K_M · 21.3 GB | ~4.7 | CPU offload |
DeepSeek-R1-Distill-Qwen 32B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
21.0 GB | ~2.4 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
21.0 GB | ~3.1 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
21.0 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
21.0 GB | 33 | Tight fit |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
21.0 GB | 32 | Tight fit |
| GeForce RTX 5090 30.4 GB usable · 1792 GB/s |
21.0 GB | 59 | Runs great |
| M4 Max · 36 GB 27.0 GB usable · 410 GB/s |
21.0 GB | 12 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
21.0 GB | 12 | Runs great |