How much memory does Mistral Small 3.2 24B need at Q4?

The Q4 figure used here is 15.7 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.

What is the cheapest catalog device that runs Mistral Small 3.2 24B at Q4?

Mac mini M4 24GB, list price $799.

How fast is Mistral Small 3.2 24B on the Mac mini M4 Pro 64GB, as a bandwidth estimate?

About 10.9 tok/s at Q8. That is device bandwidth divided by active weight bytes, not a measured run.

Yes. Mistral Small 3.2 24B fits on the Mac mini M4 Pro 64GB at Q8, with 18.4 GB of headroom. Usable memory is 44.8 GB.

Can the Mac mini M4 Pro 64GB run Mistral Small 3.2 24B?

Data updated 16 October 2026. Last reviewed the same day, when this catalog snapshot was written.

Usable memory on this 64 GB unified-memory config is 44.8 GB (70% of the sticker figure). A result under 2 GB of headroom is labeled tight.

Quant ladder

Estimated memory for Mistral Small 3.2 24B on Mac mini M4 Pro 64GB
Quant	Estimate	Headroom	Est. tok/s	Verdict
Q4	15.7 GB	29.1 GB	19.0 tok/s	Yes
Q8	26.4 GB	18.4 GB	10.9 tok/s	Yes
FP16	57.6 GB	-12.8 GB	5.68 tok/s	No

GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
Formula estimate: parameter count × bytes per weight × 1.20. No GGUF file size is stored for this quant.
Tokens/sec is a bandwidth roofline: GB/s divided by active weight GB. It is not a measured generation speed.

KV cache at 8K and 32K

FP16 KV-cache estimate: 1.3 GB at 8,192 tokens and 5.4 GB at 32,768 tokens. GQA counts two tensors (K and V) for the stored KV heads and head dimension.

Offload

This machine has one memory pool. Weights are not offloaded to a second bank of system RAM.

Ollama

This command pulls the Q4_K_M file from unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF, the Hub repo whose file size is used above. It is not an official Ollama library tag.

ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M

Other picks

Cheapest catalog device at Q4: Mac mini M4 24GB
Closest catalog model that still fits at Q4: Llama 3.3 70B Instruct.

All hardware for Mistral Small 3.2 24B · All models for the Mac mini M4 Pro 64GB

Questions

How much memory does Mistral Small 3.2 24B need at Q4?: The Q4 figure used here is 15.7 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
Can the Mac mini M4 Pro 64GB run Mistral Small 3.2 24B?: Yes. Mistral Small 3.2 24B fits on the Mac mini M4 Pro 64GB at Q8, with 18.4 GB of headroom. Usable memory is 44.8 GB.
What is the cheapest catalog device that runs Mistral Small 3.2 24B at Q4?: Mac mini M4 24GB, list price $799.
How fast is Mistral Small 3.2 24B on the Mac mini M4 Pro 64GB, as a bandwidth estimate?: About 10.9 tok/s at Q8. That is device bandwidth divided by active weight bytes, not a measured run.