Yes — with 51.0 GB to spare

DeepSeek-R1-Distill-Qwen 32B at Q4_K_M fits your M2 Max · 96 GB entirely in unified memory at 8K context, at an estimated 12 tokens per second. There is room for its full 128K window.

Fully in unified memory 8K context Q4_K_M · 18.4 GB MIT Released Jan 2025

MIT-licensed and close to the 70B distill on maths. A 24 GB card handles it at Q4.

What hardware do I need for DeepSeek-R1-Distill-Qwen 32B? →

The VRAM budget

weights 18.4 GB

Weights 18.4 GB KV cache @ 8K 2.00 GB Runtime overhead 0.6 GB Free 51.0 GB of 72.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	32.5 GB	35.1 GB	128K	6.9	−0.1% ppl	Long context
Q6_K	25.0 GB	27.6 GB	128K	8.9	−0.4% ppl	Long context
Q5_K_M	21.7 GB	24.3 GB	128K	10	−0.8% ppl	Long context
Q4_K_M	18.4 GB	21.0 GB	128K	12	−1.9% ppl	Recommended
Q3_K_M	14.9 GB	17.5 GB	128K	15	−5.4% ppl	Long context
Q2_K	12.8 GB	15.4 GB	128K	17	−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.

How to run it

Ollama llama.cpp LM Studio MLX

terminal

$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 18.4 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 72.0 GB of 96 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03There is room to go to the model's full 128K context on this card.

See all models for this rig Compare with another model