Yes — with 341.2 GB to spare

Llama 3.3 70B Instruct at Q4_K_M fits your M3 Ultra · 512 GB entirely in unified memory at 8K context, at an estimated 11 tokens per second. There is room for its full 128K window.

Fully in unified memory 8K context Q4_K_M · 39.7 GB Llama 3.3 Community Released Dec 2024

Still the creative-writing favourite: consistent voice, takes direction. Needs 48 GB to sit comfortably on GPU at Q4.

What hardware do I need for Llama 3.3 70B Instruct? →

The VRAM budget

weights 39.7 GB

Weights 39.7 GB KV cache @ 8K 2.50 GB Runtime overhead 0.6 GB Free 341.2 GB of 384.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	69.9 GB	73.0 GB	128K	6.4	−0.1% ppl	Long context
Q6_K	53.9 GB	57.0 GB	128K	8.3	−0.4% ppl	Long context
Q5_K_M	46.6 GB	49.7 GB	128K	9.6	−0.8% ppl	Long context
Q4_K_M	39.7 GB	42.8 GB	128K	11	−1.9% ppl	Recommended
Q3_K_M	32.1 GB	35.2 GB	128K	14	−5.4% ppl	Long context
Q2_K	27.5 GB	30.6 GB	128K	16	−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/Llama-3.3-70B-Instruct-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 384.0 GB of 512 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