Medical GPT OSS Swallow 120B by tokyotech-llm

 »  All LLMs  »  tokyotech-llm  »  Medical GPT OSS Swallow 120B   URL Share it on

Medical GPT OSS Swallow 120B is an open-source language model by tokyotech-llm. Features: 120b LLM, VRAM: 139.8GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.25.

  Arxiv:2508.10925 Base model:finetune:tokyotech-... Base model:tokyotech-llm/gpt-o...   Conversational   En   Endpoints compatible   Gpt oss   Ja   Japanese   Medical   Region:us   Safetensors   Sharded   Swallow   Tensorflow

Medical GPT OSS Swallow 120B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Medical GPT OSS Swallow 120B (tokyotech-llm/Medical-GPT-OSS-Swallow-120B)

Medical GPT OSS Swallow 120B Parameters and Internals

LLM NameMedical GPT OSS Swallow 120B
Repository 🤗https://huggingface.co/tokyotech-llm/Medical-GPT-OSS-Swallow-120B 
Base Model(s)  tokyotech-llm/GPT-OSS-Swallow-120B-RL-v0.1   tokyotech-llm/GPT-OSS-Swallow-120B-RL-v0.1
Model Size120b
Required VRAM139.8 GB
Updated2026-07-15
Maintainertokyotech-llm
Model Typegpt_oss
Model Files  1.2 GB: 1-of-73   4.2 GB: 2-of-73   2.2 GB: 3-of-73   4.2 GB: 4-of-73   2.2 GB: 5-of-73   4.2 GB: 6-of-73   2.2 GB: 7-of-73   4.2 GB: 8-of-73   2.2 GB: 9-of-73   4.2 GB: 10-of-73   2.2 GB: 11-of-73   4.2 GB: 12-of-73   2.2 GB: 13-of-73   4.2 GB: 14-of-73   2.2 GB: 15-of-73   4.2 GB: 16-of-73   2.2 GB: 17-of-73   4.2 GB: 18-of-73   2.2 GB: 19-of-73   4.2 GB: 20-of-73   2.2 GB: 21-of-73   4.2 GB: 22-of-73   2.2 GB: 23-of-73   4.2 GB: 24-of-73   2.2 GB: 25-of-73   4.2 GB: 26-of-73   2.2 GB: 27-of-73   4.2 GB: 28-of-73   2.2 GB: 29-of-73   4.2 GB: 30-of-73   2.2 GB: 31-of-73   4.2 GB: 32-of-73   2.2 GB: 33-of-73   4.2 GB: 34-of-73   2.2 GB: 35-of-73   4.2 GB: 36-of-73   2.2 GB: 37-of-73   4.2 GB: 38-of-73   2.2 GB: 39-of-73   4.2 GB: 40-of-73   2.2 GB: 41-of-73   4.2 GB: 42-of-73   2.2 GB: 43-of-73   4.2 GB: 44-of-73
Supported Languagesja en
Model ArchitectureGptOssForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.57.3
Vocabulary Size201088

Best Alternatives to Medical GPT OSS Swallow 120B

Best Alternatives
Context / RAM
Downloads
Likes
GPT Oss 120B128K / 65.1 GB43627535004
GPT Oss 120B128K / 65.1 GB274222
GPT Oss 120B Mxfp4 Bf16128K / 64.8 GB16532
GPT Oss Safeguard 120B128K / 65.1 GB263298
GPT Oss 120B BF16128K / 142 GB81928
Scal Lite 60B Code128K / 34.8 GB62
GPT Oss 120B Dequantized128K / 135.6 GB19610
GPT Oss 120B MLX 8bit128K / 123.7 GB3780113
GPT Oss 120B Unsloth Bnb 4bit128K / 62.1 GB1110817
GPT Oss 120B MXFP4 Q8128K / 63.7 GB730817
Note: green Score (e.g. "73.2") means that the model is better than tokyotech-llm/Medical-GPT-OSS-Swallow-120B.

Rank the Medical GPT OSS Swallow 120B Capabilities

🆘 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 55446 in total.

Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a