Yes — with 46.8 GB to spare

Qwen3.5 0.8B at Q4_K_M fits your M4 Pro · 64 GB entirely in unified memory at 8K context, at an estimated 312 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.

What hardware do I need for Qwen3.5 0.8B? →

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	94	Reference	Long context
Q8_0	0.9 GB	1.6 GB	256K	177	−0.1% ppl	Long context
Q6_K	0.7 GB	1.4 GB	256K	230	−0.4% ppl	Long context
Q5_K_M	0.6 GB	1.3 GB	256K	266	−0.8% ppl	Long context
Q4_K_M	0.5 GB	1.2 GB	256K	312	−1.9% ppl	Recommended
Q3_K_M	0.4 GB	1.1 GB	256K	385	−5.4% ppl	Long context
Q2_K	0.3 GB	1.0 GB	256K	450	−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 llama.cpp LM Studio MLX

terminal

$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3.5-0.8B-4bit \
    --max-tokens 512 --prompt "Hello"

Apple's own array framework. The fastest path on Apple Silicon. More on MLX.

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.

See all models for this rig Compare with another model