LLM EXPLORER 61,491 MODELS INDEXED

Swallow 7B Instruct AWQ by TheBloke

By TheBloke · 5 downloads
HF Repo ↗ Copy URL

Swallow 7B Instruct AWQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 4.1GB, Context: 4K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.1.

  4-bit   Awq Base model:quantized:tokyotech... Base model:tokyotech-llm/swall...   En   Instruct   Ja   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Swallow-7B-Instruct-AWQ 

Swallow 7B Instruct AWQ Parameters and Internals

LLM NameSwallow 7B Instruct AWQ
Repository 🤗https://huggingface.co/TheBloke/Swallow-7B-Instruct-AWQ 
Model NameSwallow 7B Instruct
Model Creatortokyotech-llm
Base Model(s)  Swallow 7B Instruct Hf   tokyotech-llm/Swallow-7b-instruct-hf
Model Size7b
Required VRAM4.1 GB
Updated2026-08-06
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  4.1 GB
Supported Languagesen ja
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size43176
Torch Data Typefloat16

Best Alternatives to Swallow 7B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB32
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB61
CodeLlama 7B Instruct AWQ16K / 3.9 GB2784
...ama 7B Instruct Hf W4 G128 AWQ16K / 3.9 GB60
CausalLM 7B AWQ8K / 5.8 GB53
...essianai 7B Chat Bilingual AWQ8K / 3.9 GB152
Leo Hessianai 7B Chat AWQ8K / 3.9 GB31
...epseek Math 7B Instruct AWQ Q44K / 4.8 GB60
Llama 2 7B Ft Instruct Es AWQ4K / 3.9 GB01
...i 7B Sft Qa Context Jaqket AWQ4K / 3.9 GB41
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Swallow-7B-Instruct-AWQ.