Yes — with 3.8 GB to spare

GLM-4.7-Flash 30B-A3B at Q4_K_M fits your A10 entirely on the GPU at 8K context, at an estimated 83 tokens per second. Past 82K 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 · 17.5 GB MIT Released 20 Jan 2026

MIT-licensed 30B-A3B tuned for agentic coding, with a DeepSeek-style latent KV cache. 60–80 tok/s reported on a 4090.

What hardware do I need for GLM-4.7-Flash 30B-A3B? →

The VRAM budget

weights 17.5 GB

Weights 17.5 GB KV cache @ 8K 0.41 GB Runtime overhead 0.6 GB Free 3.8 GB of 22.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	30.9 GB	31.9 GB	—	~12	−0.1% ppl	9.5 GB over
Q6_K	23.8 GB	24.8 GB	—	~32	−0.4% ppl	2.4 GB over
Q5_K_M	20.6 GB	21.6 GB	23K	71	−0.8% ppl	Long context
Q4_K_M	17.5 GB	18.6 GB	82K	83	−1.9% ppl	Recommended
Q3_K_M	14.2 GB	15.2 GB	147K	102	−5.4% ppl	Long context
Q2_K	12.2 GB	13.2 GB	186K	119	−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 uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.

How to run it

Ollama llama.cpp LM Studio vLLM

terminal

$ ollama pull glm-4.7-flash:latest
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run glm-4.7-flash:latest

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

01Download is 17.5 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 82K context on this card.

See all models for this rig Compare with another model