gpt-oss 120B

No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.

unsloth/gpt-oss-120b-GGUF:Q3_K_Sllamacpp · Q3_K_S · 58.3 GiB · quantizer (unsloth)

unsloth/gpt-oss-120b-GGUF:Q2_Kllamacpp · Q2_K · 58.3 GiB · quantizer (unsloth)

unsloth/gpt-oss-120b-GGUF:Q4_0llamacpp · Q4_0 · 58.3 GiB · quantizer (unsloth)

unsloth/gpt-oss-120b-GGUF:Q4_K_Mllamacpp · Q4_K_M · 58.5 GiB · quantizer (unsloth)

mlx-community/gpt-oss-120b-MXFP4-Q8mlx · 4BIT · 59.0 GiB · quantizer (mlx-community)

unsloth/gpt-oss-120b-GGUF:Q8_0llamacpp · Q8_0 · 59.0 GiB · quantizer (unsloth)

hf.co/ggml-org/gpt-oss-120b-GGUF:MXFP4ollama · MXFP4 · 59.0 GiB · quantizer (ggml-org)

unsloth/gpt-oss-120b-GGUF:Q8_K_XLllamacpp · Q8_K_XL · 60.0 GiB · quantizer (unsloth)

lmstudio-community/gpt-oss-120b-MLX-8bitmlx · 8BIT · 115.6 GiB · quantizer (lmstudio-community)

openai/gpt-oss-120bvllm · MXFP4 · 121.5 GiB · vendor (openai)

derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

gpt-oss-120b-Uncensorednot measured gpt-oss-120b-Fable-5-Distillednot measured gpt-oss-120b-Eagle3-short-contextnot measured gpt-oss-bf16not measured