LLM Name | GPT Oss 20B Bnb 4bit |
Repository ๐ค | https://huggingface.co/unsloth/gpt-oss-20b-bnb-4bit |
Base Model(s) | |
Model Size | 20b |
Required VRAM | 40.8 GB |
Updated | 2025-08-09 |
Maintainer | unsloth |
Model Type | gpt_oss |
Model Files | |
Quantization Type | 4bit |
Model Architecture | GptOssForCausalLM |
License | apache-2.0 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.56.0.dev0 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|reserved_200017|> |
Vocabulary Size | 201088 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
GPT Oss 20B MLX 8bit | 128K / 22.1 GB | 444241 | 19 |
GPT Oss 20B Unsloth Bnb 4bit | 128K / 12.6 GB | 519 | 6 |
GPT Oss 20B | 128K / 13.8 GB | 863986 | 2547 |
GPT Oss 20B GGUF | 128K / 11.5 GB | 253409 | 240 |
GPT Oss 20B | 128K / 13.8 GB | 2728 | 23 |
GPT Oss 20B BF16 | 128K / 41.6 GB | 3112 | 14 |
GPT Oss 20B ShiningValiant3 | 128K / 41.6 GB | 63 | 11 |
GPT Oss 20B Dequantized | 128K / 41.6 GB | 590 | 0 |
...PT OSS 26B Abliterated Preview | 128K / 51.4 GB | 6 | 2 |
...i GPT Oss 20B BF16 Abliterated | 128K / 41.6 GB | 1021 | 78 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐