Yes — with 46.8 GB to spare
Qwen3.5 0.8B at Q4_K_M fits your Ryzen AI Max+ 395 · 64 GB entirely in unified memory at 8K context, at an estimated 292 tokens per second. There is room for its full 256K window.
Fully in unified memory
8K context
Q4_K_M · 0.5 GB
Apache 2.0
Released 28 Feb 2026
Draft model for speculative decoding, or a classifier that fits in 1 GB.
The VRAM budget
weights 0.5 GB
Weights 0.5 GB
KV cache @ 8K 0.09 GB
Runtime overhead 0.6 GB
Free 46.8 GB of 48.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 1.6 GB | 2.3 GB | 256K | 88 | Reference | Long context |
| Q8_0 | 0.9 GB | 1.6 GB | 256K | 166 | −0.1% ppl | Long context |
| Q6_K | 0.7 GB | 1.4 GB | 256K | 215 | −0.4% ppl | Long context |
| Q5_K_M | 0.6 GB | 1.3 GB | 256K | 249 | −0.8% ppl | Long context |
| Q4_K_M | 0.5 GB | 1.2 GB | 256K | 292 | −1.9% ppl | Recommended |
| Q3_K_M | 0.4 GB | 1.1 GB | 256K | 361 | −5.4% ppl | Long context |
| Q2_K | 0.3 GB | 1.0 GB | 256K | 422 | −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. Only 6 of its 24 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.
How to run it
$ ollama pull qwen3.5:0.8b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run qwen3.5:0.8b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 0.5 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 256K context on this card.