Yes — with 120.9 GB to spare

Qwen3.5 122B-A10B at Q4_K_M fits your M3 Ultra · 256 GB entirely in unified memory at 8K context, at an estimated 37 tokens per second. There is room for its full 256K window.

Fully in unified memory 8K context Q4_K_M · 70.3 GB Apache 2.0 Released 24 Feb 2026 Vision

The 96–128 GB unified-memory model: 122B of knowledge at 10B-active speed.

What hardware do I need for Qwen3.5 122B-A10B? →

The VRAM budget

weights 70.3 GB

Weights 70.3 GB KV cache @ 8K 0.19 GB Runtime overhead 0.6 GB Free 120.9 GB of 192.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	123.7 GB	124.5 GB	256K	21	−0.1% ppl	Long context
Q6_K	95.5 GB	96.2 GB	256K	27	−0.4% ppl	Long context
Q5_K_M	82.5 GB	83.3 GB	256K	32	−0.8% ppl	Long context
Q4_K_M	70.3 GB	71.1 GB	256K	37	−1.9% ppl	Recommended
Q3_K_M	56.9 GB	57.7 GB	256K	46	−5.4% ppl	Long context
Q2_K	48.7 GB	49.5 GB	256K	53	−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 12 of its 48 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/Qwen3.5-122B-A10B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 70.3 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 192.0 GB of 256 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