How much memory does gpt-oss-120b need at Q4?

The Q4 figure used here is 63.1 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 gpt-oss-120b at Q4?

Framework Desktop 128GB, list price $3,449.

How fast is gpt-oss-120b on the Mac Studio M3 Ultra 96GB, as a bandwidth estimate?

About 296 tok/s at Q8. That is device bandwidth divided by active weight bytes, not a measured run.

Yes. gpt-oss-120b fits on the Mac Studio M3 Ultra 96GB at Q8, with 3.5 GB of headroom. Usable memory is 67.2 GB.

Can the Mac Studio M3 Ultra 96GB run gpt-oss-120b?

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

Usable memory on this 96 GB unified-memory config is 67.2 GB (70% of the sticker figure). A result under 2 GB of headroom is labeled tight.

Quant ladder

Estimated memory for gpt-oss-120b on Mac Studio M3 Ultra 96GB
Quant	Estimate	Headroom	Est. tok/s	Verdict
Q4	63.1 GB	4.1 GB	299 tok/s	Yes
Q8	63.7 GB	3.5 GB	296 tok/s	Yes
FP16	280 GB	-213.2 GB	80.3 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: 0.3 GB at 8,192 tokens and 1.2 GB at 32,768 tokens. GQA counts two tensors (K and V) for the stored KV heads and head dimension. config.json also sets a sliding window of 128 tokens. The figures above assume every counted layer stores the full context, so they can overstate cache on sliding layers.

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/gpt-oss-120b-GGUF, the Hub repo whose file size is used above. It is not an official Ollama library tag.

ollama run hf.co/unsloth/gpt-oss-120b-GGUF:Q4_K_M

Other picks

Cheapest catalog device at Q4: Framework Desktop 128GB
Closest catalog model that still fits at Q4: Llama 4 Scout.

All hardware for gpt-oss-120b · All models for the Mac Studio M3 Ultra 96GB

Questions

How much memory does gpt-oss-120b need at Q4?: The Q4 figure used here is 63.1 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 Studio M3 Ultra 96GB run gpt-oss-120b?: Yes. gpt-oss-120b fits on the Mac Studio M3 Ultra 96GB at Q8, with 3.5 GB of headroom. Usable memory is 67.2 GB.
What is the cheapest catalog device that runs gpt-oss-120b at Q4?: Framework Desktop 128GB, list price $3,449.
How fast is gpt-oss-120b on the Mac Studio M3 Ultra 96GB, as a bandwidth estimate?: About 296 tok/s at Q8. That is device bandwidth divided by active weight bytes, not a measured run.