Yes — with 125.4 GB to spare
GLM-4.7-Flash 30B-A3B at Q4_K_M fits your M2 Ultra · 192 GB entirely in unified memory at 8K context, at an estimated 124 tokens per second. There is room for its full 198K window.
Fully in unified memory
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
Free 125.4 GB of 144.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 30.9 GB | 31.9 GB | 198K | 70 | −0.1% ppl | Long context |
| Q6_K | 23.8 GB | 24.8 GB | 198K | 91 | −0.4% ppl | Long context |
| Q5_K_M | 20.6 GB | 21.6 GB | 198K | 105 | −0.8% ppl | Long context |
| Q4_K_M | 17.5 GB | 18.6 GB | 198K | 124 | −1.9% ppl | Recommended |
| Q3_K_M | 14.2 GB | 15.2 GB | 198K | 153 | −5.4% ppl | Long context |
| Q2_K | 12.2 GB | 13.2 GB | 198K | 178 | −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 144.0 GB of 192 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 198K context on this card.