GPT-OSS 120B

117B MoE

OpenAI GPT-OSS

The big GPT-OSS (117B total / 5.1B active). Native MXFP4 checkpoint is ~61GB — fits one 80GB card or a 128GB unified-memory Mac. Partial offload on 24GB consumer cards is slow but works.

⬇ 4.1M HF downloads♥ 5087 likesopenai/gpt-oss-120b· stats from 8/8/2026

Pro GPUMac / Apple Silicon

131K

Max Context

Quant Variants

GGUF MXFP4

Best Quality

100.0%

Accuracy Retained

Calculate VRAM Hugging Face Compare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = site benchmarks · Estimated = formula · Community = public reports

Format	Level	BPW	VRAM	PPL Loss	Speed	Source	Actions
GGUF	MXFP4	4.25	61.0 GB	0.0%	22 tok/s	Community	Calc HF
GGUF	Q4_K_M	4.1	58.5 GB	1.6%	24 tok/s	Estimated	Calc HF

Similar models

Compare with GPT-OSS 20B

21B MoE

GPT-OSS 20B

OpenAI GPT-OSS

Consumer GPUMac / Apple Silicon

11.9 GBmin VRAM·100.0%accuracy

OpenAI open-weight MoE (21B total / 3.6B active), shipped natively in MXFP4 — ~12.8GB runs on a 16GB card with no quality tax. Only 3.6B active params means CPU-offload stays usable.

106B MoE

GLM-4.5-Air

Zhipu GLM-4.5

Pro GPUMac / Apple Silicon

34.8 GBmin VRAM·97.6%accuracy

Zhipu's agentic/reasoning MoE (106B total / 12B active). Q4 ~64GB — the sweet spot is a 96GB+ unified Mac or 2× 48GB cards. Strong tool-calling for its class.

132B

DBRX Instruct

Databricks

Pro GPU

63.2 GBmin VRAM·97.5%accuracy

MoE flagship (~36B active). Needs multi-GPU; strong code and reasoning at scale.

235B-A22B

Qwen3 235B-A22B Instruct

Alibaba Qwen3

Pro GPU

115.0 GBmin VRAM·97.8%accuracy

Qwen3 flagship MoE (22B active / 235B total). Q4_K_M ~142GB; rivals DeepSeek-R1 class models.