Yes — with 3.9 GB to spare

Qwen3 Coder 30B-A3B at Q4_K_M fits your A10 entirely on the GPU at 8K context, at an estimated 75 tokens per second. Past 49K 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 · 17.1 GB Apache 2.0 Released Jul 2025

Agentic coding MoE with a 256K native window. Still the most-downloaded local code model.

What hardware do I need for Qwen3 Coder 30B-A3B? →

The VRAM budget

weights 17.1 GB

Weights 17.1 GB KV cache @ 8K 0.75 GB Runtime overhead 0.6 GB Free 3.9 GB of 22.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	30.2 GB	31.5 GB	—	~11	−0.1% ppl	9.1 GB over
Q6_K	23.3 GB	24.6 GB	—	~30	−0.4% ppl	2.2 GB over
Q5_K_M	20.1 GB	21.5 GB	17K	64	−0.8% ppl	Long context
Q4_K_M	17.1 GB	18.5 GB	49K	75	−1.9% ppl	Recommended
Q3_K_M	13.9 GB	15.2 GB	84K	93	−5.4% ppl	Long context
Q2_K	11.9 GB	13.2 GB	105K	109	−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 qwen3-coder:30b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen3-coder:30b

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

01Download is 17.1 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 49K context on this card.

See all models for this rig Compare with another model