LLM EXPLORER 58,297 MODELS INDEXED

Open Calm 7B 8bit by kyo-takano

By kyo-takano · 9 downloads

Open Calm 7B 8bit is an open-source language model by kyo-takano. Features: 7b LLM, VRAM: 7.4GB, Context: 2K, License: cc-by-sa-4.0, Quantized, LLM Explorer Score: 0.07.

  8-bit   8bit   Gpt neox   Ja   Japanese   Pytorch   Quantized   Region:us

Open Calm 7B 8bit Parameters and Internals

Model Type 
Transformer-based Language Model, causal-lm
Additional Notes 
8-bit version quantized by Kyo Takano.
Supported Languages 
ja (High)
LLM NameOpen Calm 7B 8bit
Repository πŸ€—https://huggingface.co/kyo-takano/open-calm-7b-8bit 
Model Size7b
Required VRAM7.4 GB
Updated2026-08-01
Maintainerkyo-takano
Model Typegpt_neox
Model Files  7.4 GB
Supported Languagesja
Quantization Type8bit
Model ArchitectureGPTNeoXForCausalLM
Licensecc-by-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.30.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|padding|>
Vocabulary Size52224
Torch Data Typefloat16

Best Alternatives to Open Calm 7B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Stablelm Tuned Alpha 7B 16bit4K / 16 GB125
...lm Tuned Alpha 7B Sharded 8bit4K / 8.6 GB152
Dolly V2 7B Sharded 8bit2K / 7.4 GB91
Dolly V2 7B 8bit2K / 7.4 GB70
Literature 7B 1638416K / 36 GB916
RedPajama 7B 1638416K / 36 GB84
Stablelm Tuned Alpha 7B4K / 31.9 GB713361
Stablelm Base Alpha 7B4K / 31.9 GB884208
Stablelm 7B Sft V7 Epoch 34K / 32.4 GB6467
StableLManticore 7B4K / 16 GB101
Note: green Score (e.g. "73.2") means that the model is better than kyo-takano/open-calm-7b-8bit.