openai/gpt-oss-20b
183 derivatives checked
- unsloth/gpt-oss-20b-GGUF: Same weights, converted
- mlx-community/gpt-oss-20b-MXFP4-Q8: Quantization
- ggml-org/gpt-oss-20b-GGUF: Not comparable yet
- MuXodious/gpt-oss-20b-RichardErkhov-heresy: Abliterated
- lmstudio-community/gpt-oss-20b-GGUF: Quantization
- unsloth/gpt-oss-20b-BF16: Same weights, repacked
- unsloth/gpt-oss-20b-unsloth-bnb-4bit: Quantization
- openai/gpt-oss-safeguard-20b: Partial fine-tune
- unsloth/gpt-oss-20b: Identical copy
- bartowski/openai_gpt-oss-20b-GGUF: Same weights, converted
- mlx-community/gpt-oss-20b-OptiQ-4bit: Quantization
- furiosa-ai/gpt-oss-20b: Identical copy
- lmstudio-community/gpt-oss-20b-MLX-8bit: Quantization
- amd/gpt-oss-20b-WFP8-AFP8-KVFP8: Quantization
- amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8: Quantization
- RedHatAI/gpt-oss-20b: Identical copy
- Mungert/gpt-oss-safeguard-20b-GGUF: Full fine-tune
- Mungert/DMind-3-GGUF: LoRA-style
- squ11z1/gpt-oss-nano: LoRA-style
- mlx-community/gpt-oss-20b-MXFP4-Q4: Quantization
- DavidAU/Openai_gpt-oss-20b-NEO-GGUF: Quantization
- fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf: LoRA-style
- mradermacher/gpt-oss-20b-i1-GGUF: Quantization
- artindnr/Strawberry: LoRA-style
- SoAIHQ/gpt-oss-20b-VISION-GGUF: Same weights, converted
- Mungert/gpt-oss-20b-Derestricted-GGUF: LoRA-style
- manjunathshiva/gpt-oss-20b-tq3: Quantization
- EricSpencer00/chattla-20b: LoRA-style
- tripolskypetr/gpt-oss-20b: Same weights, converted
- InferenceIllusionist/gpt-oss-20b-MLX-4bit: Quantization
114 other repos hold byte-for-byte identical weight files.