Yes — with 25.4 GB to spare

Qwen2.5-Coder 32B at Q4_K_M fits your RTX 6000 Ada entirely on the GPU at 8K context, at an estimated 32 tokens per second. Past 109K 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.

What hardware do I need for Qwen2.5-Coder 32B? →

The VRAM budget

weights 18.4 GB

Weights 18.4 GB KV cache @ 8K 2.00 GB Runtime overhead 0.6 GB Free 25.4 GB of 46.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	32.5 GB	35.1 GB	53K	18	−0.1% ppl	Long context
Q6_K	25.0 GB	27.6 GB	83K	23	−0.4% ppl	Long context
Q5_K_M	21.7 GB	24.3 GB	96K	27	−0.8% ppl	Long context
Q4_K_M	18.4 GB	21.0 GB	109K	32	−1.9% ppl	Recommended
Q3_K_M	14.9 GB	17.5 GB	123K	39	−5.4% ppl	Long context
Q2_K	12.8 GB	15.4 GB	128K	45	−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 llama.cpp LM Studio vLLM

terminal

$ ollama pull qwen2.5-coder:32b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen2.5-coder:32b

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

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.

03There is room to go to 109K context on this card.

See all models for this rig Compare with another model