Yes, just — 2.7 GB spare

LLM-jp 4 33B Thinking at Q4_K_M fits your M4 · 32 GB entirely in unified memory at 8K context, at an estimated 3.6 tokens per second. Past 18K 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 · 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 2.7 GB of 24.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	32.9 GB	35.5 GB	—	~2.0	−0.1% ppl	11.5 GB over
Q6_K	25.4 GB	28.0 GB	—	~2.6	−0.4% ppl	4.0 GB over
Q5_K_M	21.9 GB	24.5 GB	5K	~3.1	−0.8% ppl	0.5 GB over
Q4_K_M	18.7 GB	21.3 GB	18K	3.6	−1.9% ppl	Recommended
Q3_K_M	15.1 GB	17.7 GB	33K	4.4	−5.4% ppl	Long context
Q2_K	12.9 GB	15.5 GB	41K	5.2	−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 24.0 GB of 32 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03Only 2.7 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 18K context.

See all models for this rig Compare with another model