openai/gpt-oss-120b
89 derivatives checked
- ggml-org/gpt-oss-120b-GGUF: Not comparable yet
- unsloth/gpt-oss-120b-GGUF: Same weights, converted
- nvidia/gpt-oss-120b-Eagle3-short-context: Different architecture
- tiny-random/gpt-oss-bf16: Different architecture
- nvidia/gpt-oss-120b-Eagle3-v3: Different architecture
- lmstudio-community/gpt-oss-120b-MLX-8bit: Quantization
- HauhauCS/GPTOSS-120B-Uncensored-HauhauCS-Aggressive: Abliterated
- lmstudio-community/gpt-oss-120b-GGUF: Quantization
- amd/gpt-oss-120b-w-mxfp4-a-fp8: Quantization
- yujiepan/gpt-oss-tiny-random: Different architecture
- bartowski/openai_gpt-oss-120b-GGUF: Same weights, converted
- tiny-random/gpt-oss-mxfp4: Different architecture
- mlx-community/gpt-oss-120b-MXFP4-Q8: Quantization
- unsloth/gpt-oss-120b-unsloth-bnb-4bit: Quantization
- exalandru/GPT-OSS-Coder-GGUF: LoRA-style
- openai/gpt-oss-safeguard-120b: Partial fine-tune
- unsloth/gpt-oss-120b-BF16: Same weights, repacked
- unsloth/gpt-oss-120b: Identical copy
- tiny-random/gpt-oss: Different architecture
- mlx-community/gpt-oss-120b-MXFP4-Q4: Quantization
- furiosa-ai/gpt-oss-120b: Identical copy
- nvidia/gpt-oss-120b-Eagle3-long-context: Different architecture
- yujiepan/gpt-oss-tiny-random-mxfp4: Different architecture
- yujiepan/gpt-oss-tiny-random-bf16: Different architecture
- DevQuasar/openai.gpt-oss-120b-GGUF: Same weights, converted
- MultiverseComputingCAI/HyperNova-60B: Partial fine-tune
- nvidia/gpt-oss-120b-Eagle3-throughput: Different architecture
- mlx-community/gpt-oss-120b-mxfp4-bf16: Quantization
- tripolskypetr/gpt-oss-120b: Quantization
- Myric/gpt-oss-78B-GGUF: Same weights, converted
99 other repos hold byte-for-byte identical weight files.