Yes, just — 2.2 GB spare

Gemma 4 31B at Q4_K_M fits your A10 entirely on the GPU at 8K context, at an estimated 21 tokens per second. Past 21K 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 · 17.6 GB Apache 2.0 Released 2 Apr 2026 Vision

The dense flagship: strongest maths of the 24–32 GB class (89% AIME), clean prose, vision. Q4 is a tight 24 GB fit.

What hardware do I need for Gemma 4 31B? →

The VRAM budget

weights 17.6 GB

Weights 17.6 GB KV cache @ 8K 2.03 GB Runtime overhead 0.6 GB Free 2.2 GB of 22.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	31.0 GB	33.6 GB	—	~2.8	−0.1% ppl	11.2 GB over
Q6_K	23.9 GB	26.5 GB	—	~5.9	−0.4% ppl	4.1 GB over
Q5_K_M	20.7 GB	23.3 GB	2K	~13	−0.8% ppl	0.9 GB over
Q4_K_M	17.6 GB	20.2 GB	21K	21	−1.9% ppl	Recommended
Q3_K_M	14.2 GB	16.9 GB	43K	25	−5.4% ppl	Long context
Q2_K	12.2 GB	14.8 GB	56K	30	−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. This model interleaves sliding-window layers (1024 tokens, 10 of 60 layers global), which is why its cache barely grows with context.

How to run it

Ollama llama.cpp LM Studio vLLM

terminal

$ llama-server \
    -hf google/gemma-4-31B-it:Q4_K_M \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 17.6 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 2.2 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 21K context.

See all models for this rig Compare with another model