LLM EXPLORER 59,516 MODELS INDEXED

Mosaicml Mpt 7B Chat W4 G128 AWQ by abhinavkulkarni

By abhinavkulkarni · 15 downloads
HF Repo ↗ Copy URL

Mosaicml Mpt 7B Chat W4 G128 AWQ is an open-source language model by abhinavkulkarni. Features: 7b LLM, VRAM: 3.8GB, License: cc-by-sa-3.0, Quantized, LLM Explorer Score: 0.08.

  Awq   Custom code   Mosaicml   Mpt   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/abhinavkulkarni/mosaicml-mpt-7b-chat-w4-g128-awq 

Mosaicml Mpt 7B Chat W4 G128 AWQ Parameters and Internals

Model Type 
dialogue generation, chatbot
Additional Notes 
The model is a 4-bit 128-group AWQ quantized version of the MPT-7B-Chat.
Input Output 
Accepted Modalities:
text
LLM NameMosaicml Mpt 7B Chat W4 G128 AWQ
Repository 🤗https://huggingface.co/abhinavkulkarni/mosaicml-mpt-7b-chat-w4-g128-awq 
Model Size7b
Required VRAM3.8 GB
Updated2026-07-31
Maintainerabhinavkulkarni
Model Typempt
Model Files  3.8 GB   3.8 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMPTForCausalLM
Licensecc-by-sa-3.0
Model Max Length2048
Transformers Version4.33.1
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50432
Torch Data Typefloat16

Best Alternatives to Mosaicml Mpt 7B Chat W4 G128 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mpt 7B 8K Chat AWQ0K / 3.8 GB203
Mpt 7B AWQ0K / 3.8 GB60
Mpt 7B Chat 8K 4bit AWQ0K / 3.8 GB61
...ml Mpt 7B Instruct W4 G128 AWQ0K / 3.8 GB50
Mpt 7B Chat Q80K / 6.9 GB161
Mpt 7B Storywriter Q80K / 6.9 GB132
Mpt 7B Instruct Q80K / 6.9 GB172
Mpt 7B Q80K / 6.9 GB131
Mpt 7B Storywriter 4bit 128g0K / 3.9 GB194127
...writer 4bit 128g 65kTokens CPU0K / 3.9 GB159
Note: green Score (e.g. "73.2") means that the model is better than abhinavkulkarni/mosaicml-mpt-7b-chat-w4-g128-awq.