LLM EXPLORER 57,918 MODELS INDEXED

GPT Oss 20B Offload by myselfsaurabh

By myselfsaurabh · 8 downloads

GPT Oss 20B Offload is an open-source language model by myselfsaurabh. Features: 20b LLM, VRAM: 41.6GB, Context: 128K, License: mit, LLM Explorer Score: 0.19.

  Colab   Conversational   Cpu-gpu-offload Dataset:openai/gpt-oss-trainin...   En   Gpt-oss   Gpt oss   Mixture-of-experts   Mxfp4   Openai   Region:us   Safetensors   Sharded   Tensorflow

GPT Oss 20B Offload Parameters and Internals

LLM NameGPT Oss 20B Offload
Repository πŸ€—https://huggingface.co/myselfsaurabh/gpt-oss-20b-offload 
Model Size20b
Required VRAM41.6 GB
Updated2026-07-28
Maintainermyselfsaurabh
Model Typegpt_oss
Model Files  4.5 GB: 1-of-9   4.9 GB: 2-of-9   4.9 GB: 3-of-9   4.9 GB: 4-of-9   4.9 GB: 5-of-9   4.9 GB: 6-of-9   4.9 GB: 7-of-9   4.9 GB: 8-of-9   2.8 GB: 9-of-9
Supported Languagesen
Model ArchitectureGptOssForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.56.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size201088
Torch Data Typebfloat16

Best Alternatives to GPT Oss 20B Offload

Best Alternatives
Context / RAM
Downloads
Likes
GPT Oss 20B128K / 13.8 GB79836204849
OTel LLM 20B Reasoning128K / 83.8 GB10401
GPT Oss 20B128K / 13.8 GB1641647
Strawberry 1128K / 41.6 GB4062
Context 1128K / 41.8 GB726414
GPT Oss Safeguard 20B128K / 13.8 GB154333239
GPT Oss 20B Heretic Ara V4128K / 13.8 GB533913
OptiMind SFT128K / 42 GB15767102
GPT Oss 20B BF16128K / 41.6 GB9687434
GPT Oss 20B Heretic128K / 41.6 GB2413124
Note: green Score (e.g. "73.2") means that the model is better than myselfsaurabh/gpt-oss-20b-offload.