~/model/huggingfaceopenai/gpt-oss-120b
OpenAI

gpt-oss 120B

OpenAI's open-weight flagship. Near o4-mini on core reasoning; MXFP4 deployment fits a single 80GB H100.

Parameters
117B
Family
OpenAI
Context
128K tokens
FP16 weights
234GB
// where you can run it
gpt-oss:120bLM StudiovLLMMLXoMLX
// hugging face stats (cached daily)
4.9M downloads · 5K likes · license: apache-2.0 · updated 8 months ago

What you need to run this.

$ ./vrambudget --model gpt-oss-120b --by quant
FP16234 GB
M3 Ultra 512512 GB · fitsM2 Ultra 192192 GB · overB200192 GB · overMI300X192 GB · over
Q8_0124 GB
2× H100 NVL188 GB · fitsM2 Ultra 192192 GB · fitsB200192 GB · fitsMI300X192 GB · fits
Q6_K96 GB
M4 Max 128128 GB · fitsM5 Max 128128 GB · fitsDGX Spark128 GB · fitsGaudi 3128 GB · fits
Q5_K_M80 GB
M4 Max 128128 GB · fitsM5 Max 128128 GB · fitsDGX Spark128 GB · fitsGaudi 3128 GB · fits
Q4_K_M66 GB
M3 Max 9696 GB · fitsRTX Pro 600096 GB · fitsM4 Max 128128 GB · fitsM5 Max 128128 GB · fits

// budgets shown at ctx 8K, concurrency 1, 15% safety headroom. Tune in the calculator →

Alternatives at this size.

$ grep --params similar catalog.json
$ similarCommand R+104BCohere$ similarMixtral 8x22B141BMistral$ similarQwen 2.5 72B72.7BAlibaba$ similarLlama 3.3 70B70.6BMeta

Discussion.

$ gh discussion list

// sign in with github to leave a comment. threads live in the repo's discussions tab.