GPT-OSS 120B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
OpenAI's first large open-weight release. Dense 120B model at Q4_K_M fits in ~65 GB VRAM — dual RTX 3090 or single A100 80GB. Matches GPT-4o on MMLU (87.4%), MATH (78.9%), and HumanEval (88.5%). The go-to choice for enterprise teams that need GPT-4-class quality without API costs or data privacy concerns.
GPT-OSS 120B needs about 71 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 39.5 GB | ~32 tok/s | Offload | |
| Q3_K_M 3.41 bpw | 50.9 GB | ~28 tok/s | Offload | |
| Q4_K_M 4.83 bpw | 71.6 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 83.9 GB | — | Too big | |
| Q6_K 6.56 bpw | 96.9 GB | — | Too big | |
| Q8_0 8.50 bpw | 125.2 GB | — | Too big | |
| F16 16.00 bpw | 234.7 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. GPT-OSS 120B VRAM calculator →
Get GPT-OSS 120B running
The cheapest catalogued GPU that runs GPT-OSS 120B is the NVIDIA DGX Spark (128 GB).
or compare on Vast.ai from $0.77/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run GPT-OSS 120B
Install Ollama, then run:
ollama run gpt-oss:120bSpecifications
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- Parameters
- 116.8B (5.1B active)
- Context window
- 131,072
- Architecture
- Mixture-of-Experts (128 experts, top-4, MXFP4)
- Provider
- OpenAI
- Licence
- Apache 2.0
- Practical deployment
- Workstation (large unified memory or pro GPU)
- Specified at
- Q4_K_M
- System RAM
- 128 GB
- Record updated
- 2026-04-01
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
| Benchmark | Score | Provenance |
|---|---|---|
| MMLU | 87.4 / 100 % | reported |
| MATH | 78.9 / 100 % | reported |
| HumanEval | 88.5 / 100 % | reported |
Can I run GPT-OSS 120B on my GPU?
- GPT-OSS 120B on AMD Radeon RX 7800 XT
- GPT-OSS 120B on AMD Radeon RX 7900 XT
- GPT-OSS 120B on AMD Radeon RX 7900 XTX
- GPT-OSS 120B on AMD Radeon RX 9060 XT 16GB
- GPT-OSS 120B on AMD Radeon RX 9060 XT 8GB
- GPT-OSS 120B on AMD Radeon RX 9070
- GPT-OSS 120B on AMD Radeon RX 9070 XT
- GPT-OSS 120B on AMD Ryzen AI Max+ 395
- GPT-OSS 120B on Apple M1
- GPT-OSS 120B on Apple M1 Ultra
- GPT-OSS 120B on Apple M2
- GPT-OSS 120B on Apple M2 Max
- GPT-OSS 120B on Apple M3
- GPT-OSS 120B on Apple M4 Max
- GPT-OSS 120B on Apple M4 Pro
- GPT-OSS 120B on Apple M5 Max
- GPT-OSS 120B on Intel Arc B570
- GPT-OSS 120B on Intel Arc B580
- GPT-OSS 120B on NVIDIA A100 80GB (PCIe)
- GPT-OSS 120B on NVIDIA DGX Spark
- GPT-OSS 120B on NVIDIA GeForce RTX 3060 (12GB)
- GPT-OSS 120B on NVIDIA GeForce RTX 3070
- GPT-OSS 120B on NVIDIA GeForce RTX 3070 Ti
- GPT-OSS 120B on NVIDIA GeForce RTX 3080 (10GB)
- GPT-OSS 120B on NVIDIA GeForce RTX 3090
- GPT-OSS 120B on NVIDIA GeForce RTX 4060
- GPT-OSS 120B on NVIDIA GeForce RTX 4060 Ti 16GB
- GPT-OSS 120B on NVIDIA GeForce RTX 4070
- GPT-OSS 120B on NVIDIA GeForce RTX 4070 Super
- GPT-OSS 120B on NVIDIA GeForce RTX 4070 Ti
- GPT-OSS 120B on NVIDIA GeForce RTX 4070 Ti Super
- GPT-OSS 120B on NVIDIA GeForce RTX 4080
- GPT-OSS 120B on NVIDIA GeForce RTX 4080 Super
- GPT-OSS 120B on NVIDIA GeForce RTX 4090
- GPT-OSS 120B on NVIDIA GeForce RTX 5060
- GPT-OSS 120B on NVIDIA GeForce RTX 5060 Ti 16GB
- GPT-OSS 120B on NVIDIA GeForce RTX 5060 Ti 8GB
- GPT-OSS 120B on NVIDIA GeForce RTX 5070
- GPT-OSS 120B on NVIDIA GeForce RTX 5070 Ti
- GPT-OSS 120B on NVIDIA GeForce RTX 5080
- GPT-OSS 120B on NVIDIA H100 80GB (PCIe)
- GPT-OSS 120B on NVIDIA RTX PRO 6000 Blackwell
Other GPT-OSS sizes
GPT-OSS 120B — frequently asked questions
How much VRAM does GPT-OSS 120B need?
About 71 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does GPT-OSS 120B run on an RTX 4090 (24 GB)?
No. GPT-OSS 120B needs about 71 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run GPT-OSS 120B locally?
Install Ollama and run `ollama run gpt-oss:120b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does GPT-OSS come in?
GPT-OSS 120B (71 GB), GPT-OSS 20B (13 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.