Yes — with 4.6 GB to spare
Qwen2.5-Coder 32B at Q4_K_M fits your CPU only · DDR4 dual-channel entirely on the GPU at 8K context, at an estimated 1.2 tokens per second. Past 26K 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
Apache 2.0
Released Nov 2024
The first local code model that felt competitive with hosted assistants. Qwen3.8 27B is smaller and far ahead on agentic work.
The VRAM budget
weights 18.4 GB
Weights 18.4 GB
KV cache @ 8K 2.00 GB
Runtime overhead 0.6 GB
Free 4.6 GB of 25.6 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 32.5 GB | 35.1 GB | — | ~0.7 | −0.1% ppl | 9.5 GB over |
| Q6_K | 25.0 GB | 27.6 GB | — | ~0.9 | −0.4% ppl | 2.0 GB over |
| Q5_K_M | 21.7 GB | 24.3 GB | 13K | 1.0 | −0.8% ppl | Fits |
| Q4_K_M | 18.4 GB | 21.0 GB | 26K | 1.2 | −1.9% ppl | Recommended |
| Q3_K_M | 14.9 GB | 17.5 GB | 40K | 1.4 | −5.4% ppl | Long context |
| Q2_K | 12.8 GB | 15.4 GB | 48K | 1.7 | −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 Qwen/Qwen2.5-Coder-32B-Instruct: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.
02With no GPU, thread count matters more than clock. Start at one thread per physical core.
03There is room to go to 26K context on this card.