GPT-OSS 120B
117B MoEOpenAI 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.
131K
Max Context
2
Quant Variants
GGUF MXFP4
Best Quality
100.0%
Accuracy Retained
Quantization Variants
Per-quant VRAM, quality loss, and inference speed on RTX 4090
Measured = site benchmarks · Estimated = formula · Community = public reports
Similar models
Compare with GPT-OSS 20BGPT-OSS 20B
OpenAI GPT-OSS
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.
GLM-4.5-Air
Zhipu GLM-4.5
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.
DBRX Instruct
Databricks
MoE flagship (~36B active). Needs multi-GPU; strong code and reasoning at scale.
Qwen3 235B-A22B Instruct
Alibaba Qwen3
Qwen3 flagship MoE (22B active / 235B total). Q4_K_M ~142GB; rivals DeepSeek-R1 class models.
Running GPT-OSS 120B locally
At Q4_K_M and 4K of context, GPT-OSS 120B needs about 62.9 GB — 56.9 GB of weights, 0.28 GB of KV cache and a 5.7 GB activation buffer. The smallest card in this index that clears that comfortably is the A100 80G at 80 GB, and 11 of the 63 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.
What longer context costs
Going from 4K to 32K adds about 1.97 GB, taking the total to 65.0 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4_K_M would need about 72 GB.
Which build to download
This index only tracks GPT-OSS 120B in GGUF, across 2 levels (MXFP4, Q4_K_M). MXFP4 carries the lowest published perplexity loss at 0.0%. The fastest level measured here is Q4_K_M at 24 tok/s on an RTX 4090, batch 1. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 and CUDA only.
Common questions
- How much VRAM does GPT-OSS 120B need?
- About 62.9 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 65.0 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
- Will GPT-OSS 120B run on a 80GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 62.9 GB, which leaves 17.1 GB spare on a A100 80G. That is the smallest card in this index that clears it comfortably; 11 of 63 do.
- Which quantization of GPT-OSS 120B should I use?
- MXFP4 has the lowest published quality loss (0.0%), and Q4_K_M is the level most people run. All 2 levels in the index are MXFP4, Q4_K_M.
Where this model fits
Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.
How to actually run this
Deployment guides for this model and this class of hardware.
This page's figures change when the model or the runtime does.Last updated 2026-09-21 RSS → /feed.xml