Yes — with 29.2 GB to spare

DeepSeek-R1-Distill-Llama 70B at Q4_K_M fits your M2 Max · 96 GB entirely in unified memory at 8K context, at an estimated 5.6 tokens per second. Past 101K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully in unified memory 8K context Q4_K_M · 39.7 GB MIT / Llama 3.3 Community Released Jan 2025

The strongest of the R1 distills, and the one that most needs 48 GB or more.

What hardware do I need for DeepSeek-R1-Distill-Llama 70B? →

The VRAM budget

weights 39.7 GB
Weights 39.7 GB KV cache @ 8K 2.50 GB Runtime overhead 0.6 GB Free 29.2 GB of 72.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 69.9 GB 73.0 GB 4K ~3.2 −0.1% ppl 1.0 GB over
Q6_K 53.9 GB 57.0 GB 55K 4.1 −0.4% ppl Long context
Q5_K_M 46.6 GB 49.7 GB 79K 4.8 −0.8% ppl Long context
Q4_K_M 39.7 GB 42.8 GB 101K 5.6 −1.9% ppl Recommended
Q3_K_M 32.1 GB 35.2 GB 125K 7.0 −5.4% ppl Long context
Q2_K 27.5 GB 30.6 GB 128K 8.1 −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

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/DeepSeek-R1-Distill-Llama-70B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 39.7 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 101K context on this card.
See all models for this rig Compare with another model