Yes — with 74.7 GB to spare

LLM-jp 4 33B Thinking at Q4_K_M fits your M3 Max · 128 GB entirely in unified memory at 8K context, at an estimated 12 tokens per second. There is room for its full 64K window.

Fully in unified memory 8K context Q4_K_M · 18.7 GB Apache 2.0 Released 14 Aug 2026 New this week Not in the Ollama library

Japan’s national-institute reasoning model, Japanese and English. A plain dense Llama-style 33B: Q4 is a tight 24 GB fit.

What hardware do I need for LLM-jp 4 33B Thinking? →

The VRAM budget

weights 18.7 GB

Weights 18.7 GB KV cache @ 8K 2.00 GB Runtime overhead 0.6 GB Free 74.7 GB of 96.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	32.9 GB	35.5 GB	64K	6.8	−0.1% ppl	Long context
Q6_K	25.4 GB	28.0 GB	64K	8.8	−0.4% ppl	Long context
Q5_K_M	21.9 GB	24.5 GB	64K	10	−0.8% ppl	Long context
Q4_K_M	18.7 GB	21.3 GB	64K	12	−1.9% ppl	Recommended
Q3_K_M	15.1 GB	17.7 GB	64K	15	−5.4% ppl	Long context
Q2_K	12.9 GB	15.5 GB	64K	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

llama.cpp LM Studio MLX

terminal

$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/llm-jp-4-33b-thinking-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 18.7 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 96.0 GB of 128 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03There is room to go to the model's full 64K context on this card.

See all models for this rig Compare with another model