Yes — with 19.3 GB to spare

Qwen3.8 27B at Q4_K_M fits your M4 Pro · 48 GB entirely in unified memory at 8K context, at an estimated 9.8 tokens per second. There is room for its full 256K window.

Fully in unified memory 8K context Q4_K_M · 15.6 GB Apache 2.0 Released 14 Aug 2026 New this week Vision

The current default local Qwen: dense 27B, text + image + video, 262K context. Only 16 of its 64 blocks keep a KV cache, so long context is cheap.

What hardware do I need for Qwen3.8 27B? →

The VRAM budget

weights 15.6 GB

Weights 15.6 GB KV cache @ 8K 0.50 GB Runtime overhead 0.6 GB Free 19.3 GB of 36.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	27.5 GB	28.6 GB	126K	5.5	−0.1% ppl	Long context
Q6_K	21.2 GB	22.3 GB	226K	7.2	−0.4% ppl	Long context
Q5_K_M	18.4 GB	19.5 GB	256K	8.3	−0.8% ppl	Long context
Q4_K_M	15.6 GB	16.7 GB	256K	9.8	−1.9% ppl	Recommended
Q3_K_M	12.7 GB	13.8 GB	256K	12	−5.4% ppl	Long context
Q2_K	10.8 GB	11.9 GB	256K	14	−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 16 of its 64 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/Qwen3.8-27B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 15.6 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 36.0 GB of 48 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