No — not on this device
GLM-4.7-Flash 30B-A3B at Q4_K_M needs 18.6 GB against 18.0 GB usable, and the shortfall of 0.6 GB is more than 256 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
Does not fit
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.
The VRAM budget
weights 17.5 GB
Weights 17.5 GB
KV cache @ 8K 0.41 GB
Runtime overhead 0.6 GB
Over budget 0.6 GB past 18.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 30.9 GB | 31.9 GB | — | ~8.8 | −0.1% ppl | 13.9 GB over |
| Q6_K | 23.8 GB | 24.8 GB | — | ~11 | −0.4% ppl | 6.8 GB over |
| Q5_K_M | 20.6 GB | 21.6 GB | — | ~13 | −0.8% ppl | 3.6 GB over |
| Q4_K_M | 17.5 GB | 18.6 GB | — | ~15 | −1.9% ppl | 0.6 GB over |
| Q3_K_M | 14.2 GB | 15.2 GB | 61K | 19 | −5.4% ppl | Long context |
| Q2_K | 12.2 GB | 13.2 GB | 101K | 22 | −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
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/GLM-4.7-Flash-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
01Download is 17.5 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 18.0 GB of 24 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.