gpt-oss 20B

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.

hf.co/unsloth/gpt-oss-20b-GGUF:Q3_K_Sollama · Q3_K_S · 10.7 GiB · quantizer (unsloth)

hf.co/unsloth/gpt-oss-20b-GGUF:Q2_Kollama · Q2_K · 10.7 GiB · quantizer (unsloth)

hf.co/unsloth/gpt-oss-20b-GGUF:Q4_0ollama · Q4_0 · 10.7 GiB · quantizer (unsloth)

hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_Mollama · Q4_K_M · 10.8 GiB · quantizer (unsloth)

mlx-community/gpt-oss-20b-MXFP4-Q8mlx · 4BIT · 11.2 GiB · quantizer (mlx-community)

hf.co/unsloth/gpt-oss-20b-GGUF:Q8_0ollama · Q8_0 · 11.3 GiB · quantizer (unsloth)

hf.co/unsloth/gpt-oss-20b-GGUF:Q8_K_XLollama · Q8_K_XL · 12.3 GiB · quantizer (unsloth)

hf.co/unsloth/gpt-oss-20b-GGUF:F16ollama · F16 · 12.8 GiB · quantizer (unsloth)

lmstudio-community/gpt-oss-20b-MLX-8bitmlx · 8BIT · 20.7 GiB · quantizer (lmstudio-community)

openai/gpt-oss-20bvllm · MXFP4 · 25.6 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-20b-Derestrictednot measured openai_gpt-oss-20b-GGUF-MXFP4-Experimentalnot measured OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensorednot measured OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4not measured Huihui-gpt-oss-20b-BF16-abliteratednot measured gpt-oss-20b-bf16not measured gpt-oss-20b-tq3not measured gpt-oss-20b-OptiQ-4bitnot measured InternVL3_5-GPT-OSS-20B-A4B-Preview-HFnot measured gpt-oss-20b-hereticnot measured gpt-oss-20b-unsloth-bnb-4bitnot measured