Yes, just — 1.4 GB spare
DeepSeek-R1-Distill-Qwen 32B at Q4_K_M fits your A10 entirely on the GPU at 8K context, at an estimated 20 tokens per second. Past 13K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Fully on GPU
8K context
Q4_K_M · 18.4 GB
MIT
Released Jan 2025
MIT-licensed and close to the 70B distill on maths. A 24 GB card handles it at Q4.
The VRAM budget
weights 18.4 GB
Weights 18.4 GB
KV cache @ 8K 2.00 GB
Runtime overhead 0.6 GB
Free 1.4 GB of 22.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 32.5 GB | 35.1 GB | — | ~2.5 | −0.1% ppl | 12.7 GB over |
| Q6_K | 25.0 GB | 27.6 GB | — | ~5.0 | −0.4% ppl | 5.2 GB over |
| Q5_K_M | 21.7 GB | 24.3 GB | — | ~9.5 | −0.8% ppl | 1.9 GB over |
| Q4_K_M | 18.4 GB | 21.0 GB | 13K | 20 | −1.9% ppl | Recommended |
| Q3_K_M | 14.9 GB | 17.5 GB | 27K | 24 | −5.4% ppl | Long context |
| Q2_K | 12.8 GB | 15.4 GB | 36K | 28 | −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
$ llama-server \
-hf deepseek-ai/DeepSeek-R1-Distill-Qwen-32B:Q4_K_M \
-c 8192 -ngl 99
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
01Download is 18.4 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03Only 1.4 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 13K context.