Yes — with 29.4 GB to spare
GLM-4.7-Flash 30B-A3B at Q4_K_M fits your Ryzen AI Max+ 395 · 64 GB entirely in unified memory at 8K context, at an estimated 40 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 29.4 GB of 48.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 30.9 GB | 31.9 GB | 198K | 22 | −0.1% ppl | Long context |
| Q6_K | 23.8 GB | 24.8 GB | 198K | 29 | −0.4% ppl | Long context |
| Q5_K_M | 20.6 GB | 21.6 GB | 198K | 34 | −0.8% ppl | Long context |
| Q4_K_M | 17.5 GB | 18.6 GB | 198K | 40 | −1.9% ppl | Recommended |
| Q3_K_M | 14.2 GB | 15.2 GB | 198K | 49 | −5.4% ppl | Long context |
| Q2_K | 12.2 GB | 13.2 GB | 198K | 57 | −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 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.
02macOS caps what the GPU may wire down at about 48.0 GB of 64 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.