LLM EXPLORER 65,548 MODELS INDEXED

SeaLLM 7B V2.5 4bit by saksornr

By saksornr · 5 downloads
HF Repo ↗ Copy URL

SeaLLM 7B V2.5 4bit is an open-source language model by saksornr. Features: 7b LLM, VRAM: 5.6GB, Context: 8K, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.

  4-bit   4bit Base model:quantized:seallms/s... Base model:seallms/seallm-7b-v...   Bitsandbytes   Conversational   En   Endpoints compatible   Gemma   Quantized   Region:us   Safetensors   Th Transformers accelerate bitsan...   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/saksornr/SeaLLM-7B-v2.5-4bit 

SeaLLM 7B V2.5 4bit Parameters and Internals

Model Type 
text-generation
Additional Notes 
Uploaded model pre-quantized for faster loading.
Supported Languages 
en (English), th (Thai)
LLM NameSeaLLM 7B V2.5 4bit
Repository 🤗https://huggingface.co/saksornr/SeaLLM-7B-v2.5-4bit 
Base Model(s)  SeaLLMs/SeaLLM-7B-v2.5   SeaLLMs/SeaLLM-7B-v2.5
Model Size7b
Required VRAM5.6 GB
Updated2026-08-07
Maintainersaksornr
Model Typegemma
Model Files  5.6 GB
Supported Languagesen th
Quantization Type4bit
Model ArchitectureGemmaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to SeaLLM 7B V2.5 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...t Cleaner Gemma 32k Merged 16b31K / 17.1 GB70
...ruct Malayalam Model Vllm 4bit16K / 5.6 GB50
Gemma 1.1 7B It 4bit8K / 5.9 GB684
Gemma 1.1 7B It 4bit8K / 5.9 GB51
Gemma 7B 8bit8K / 9.4 GB31
... Codegemma 2 7B It Alpaca V1.28K / 17.1 GB350
Codegemma 7B It 8bit8K / 9.5 GB2036
Fbt Gemma 7B8K / 17.1 GB180
Codegemma 7B It 4bit8K / 5.9 GB892
Codegemma 7B 4bit8K / 5.9 GB480
Note: green Score (e.g. "73.2") means that the model is better than saksornr/SeaLLM-7B-v2.5-4bit.