gpt-oss-120b hardware requirements
About the model
- Parameters
- 116.8B total · 5.1B active (MoE)
- Attention
- Sliding-window attention
- Max context
- 131,072 tokens
- Released
- 2025-08-05
- Model card
- gpt-oss-120b on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| MXFP4baseline | 63.39 GB | Near-lossless | llama.cpp team · ggml-org |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k |
|---|---|---|---|---|---|---|
| MXFP4 | 64.1 | 64.3 | 64.6 | 65.4 | 66.9 | 69.9 |
Which GPUs can run gpt-oss-120b?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| Apple M2 Ultra · 128 GB | Runs great | 79.7 tok/s8k estimate 75.6 tok/s (60.5–90.7, calibrated estimate ±20%)measured (1 run, 2k context) | MXFP4 | 64.3 / 89.6 GB | Unified memory | up to 128k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 77.4 tok/s61.9–92.8calibrated estimate ±20% | MXFP4 | 64.3 / 67.2 GB | Unified memory | up to 64k | — | — |
| Apple M5 Max (40-core GPU) · 128 GB | Runs great | est. 60.0 tok/s48.0–72.0calibrated estimate ±20% | MXFP4 | 64.3 / 89.6 GB | Unified memory | up to 64k | — | — |
| Apple M4 Max (40-core GPU) · 128 GB | Runs great | est. 53.4 tok/s42.7–64.0calibrated estimate ±20% | MXFP4 | 64.3 / 89.6 GB | Unified memory | up to 64k | — | — |
| Ryzen AI Max+ 395 (Strix Halo) · 128 GB | Runs great | 50.2 tok/s8k estimate 44.2 tok/s (35.4–53.0, calibrated estimate ±20%)measured (1 run, 2k context) | MXFP4 | 64.3 / 89.6 GB | Unified memory | up to 32k | — | $1,999 launch MSRP |
| NVIDIA DGX Spark · 128 GB | Runs great | 35.0 tok/s8k estimate 35.6 tok/s (28.5–42.7, calibrated estimate ±20%)measured (1 run, 2k context) | MXFP4 | 64.3 / 89.6 GB | Unified memory | up to 16k | — | $3,999 launch MSRP |
| DDR5-6000 dual-channel CPU · 96 GB | Runs slowly | est. 13.4 tok/s10.8–16.1calibrated estimate ±20% | MXFP4 | 63.7 GB RAM | CPU only | up to 128k |
| — |
| DDR5-5600 dual-channel CPU · 96 GB | Runs slowly | est. 12.6 tok/s10.0–15.1calibrated estimate ±20% | MXFP4 | 63.7 GB RAM | CPU only | up to 128k |
| — |
| Apple M4 · 32 GB | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| Apple M4 Max (32-core GPU) · 48 GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| Apple M4 Pro · 64 GB | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| Apple M5 · 32 GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| Apple M5 Max (32-core GPU) · 48 GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| Apple M5 Pro · 64 GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| Intel Arc B580 | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $290 street (as of 2026-08-09) |
| DDR4-3200 dual-channel CPU · 64 GB | Won't run | — | MXFP4 | needs 63.7 GB | — | — |
| — |
| GeForce GTX 1080 Ti | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 2080 Ti | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 3050 8GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $249 launch MSRP |
| GeForce RTX 3060 12GB | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| $250 street (as of 2026-08-09) |
| GeForce RTX 3070 | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 3080 10GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 3080 12GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 3090 | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| $1,050 street (as of 2026-08-09) |
| GeForce RTX 3090 Ti | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $1,999 launch MSRP |
| GeForce RTX 4060 | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| $299 launch MSRP |
| GeForce RTX 4060 Laptop | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| GeForce RTX 4060 Ti 16GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $399 launch MSRP |
| GeForce RTX 4070 | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Laptop | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| GeForce RTX 4070 Super | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Ti Super | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 4080 | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $1,199 launch MSRP |
| GeForce RTX 4080 Laptop | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| GeForce RTX 4080 Super | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 4090 | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| $2,755 street (as of 2026-08-09) |
| GeForce RTX 4090 Laptop | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| GeForce RTX 5060 | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $429 street (as of 2026-08-09) |
| GeForce RTX 5070 | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $949 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| GeForce RTX 5080 | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $1,256 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| GeForce RTX 5090 | Won't runDetails | — | MXFP4 | needs 64.3 GB | — | — |
| $4,200 street (as of 2026-08-09) |
| GeForce RTX 5090 Laptop | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| — |
| Radeon RX 7800 XT | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $499 launch MSRP |
| Radeon RX 7900 XT | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $899 launch MSRP |
| Radeon RX 7900 XTX | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $999 launch MSRP |
| Radeon RX 9060 XT 16GB | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $449 street (as of 2026-08-09) |
| Radeon RX 9070 | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Won't run | — | MXFP4 | needs 64.3 GB | — | — |
| $689 street (as of 2026-08-09) |
Reasoning models spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s).
Cheapest GPUs that run it
No GPU with a current street price reaches Runs great or Runs well at MXFP4. The table above lists Macs, unified-memory PCs and CPU setups.
Measured results for gpt-oss-120b
Public benchmarks we calibrate against. Their conditions (context, backend, flags) can differ from the estimates above.
| Hardware | Quant | Backend | Context | Prompt (tok/s) | Generation (tok/s) | Flags | Source | Measured |
|---|---|---|---|---|---|---|---|---|
| Apple M2 Ultra | MXFP4 | llama.cpp | 2k | 1,245.0 | 79.7 | — | github.com | 2025-08-15 |
| Ryzen AI Max+ 395 (Strix Halo) | MXFP4 | llama.cpp | 2k | 707.0 | 50.2 | ROCm7 | quozul.dev | 2025-10-27 |
| NVIDIA DGX Spark | MXFP4 | llama.cpp | 2k | 1,717.0 | 35.0 | — | github.com | 2025-10-14 |
| GeForce RTX 5090 | MXFP4 | llama.cpp | 4k | — | 9.6 | --n-cpu-moe 21, DDR4 server | hardware-corner.net | 2026-08-09 |
Frequently asked questions
How much VRAM does gpt-oss-120b need?
At MXFP4 the weights are 63.39 GB; with 8k context the total is about 64.3 GB (KV cache 0.3 GB, compute buffer 0.6 GB).
What is the cheapest GPU that runs gpt-oss-120b well?
No GPU with a current street price reaches Runs great or Runs well at MXFP4. The best tracked option is Apple M2 Ultra · 128 GB: Runs great.
Can gpt-oss-120b run on an 8 GB, 16 GB or 24 GB GPU?
At MXFP4 with 8k context: GeForce RTX 4060 — Won't run; GeForce RTX 5060 Ti 16GB — Won't run; GeForce RTX 3090 — Won't run.
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.