LLM EXPLORER 60,828 MODELS INDEXED

Mistral 7B Instruct V0.3 GPTQ 8B by cortecs

By cortecs · 3 downloads
HF Repo ↗ Copy URL

Mistral 7B Instruct V0.3 GPTQ 8B is an open-source language model by cortecs. Features: 7b LLM, VRAM: 7.7GB, Context: 32K, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

  8-bit   8bit   Conversational   Dataset:wikitext   Endpoints compatible   Gptq   Instruct   Mistral   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/cortecs/Mistral-7B-Instruct-v0.3-GPTQ-8b 

Mistral 7B Instruct V0.3 GPTQ 8B Parameters and Internals

Model Type 
multilingual, text generation
Additional Notes 
We did not check for data contamination. Evaluation was done using Eval. Harness using limit=1000.
LLM NameMistral 7B Instruct V0.3 GPTQ 8B
Repository 🤗https://huggingface.co/cortecs/Mistral-7B-Instruct-v0.3-GPTQ-8b 
Base Model(s)  Finetuned Mistral On Ads   not-lain/finetuned_mistral_on_ads
Model Size7b
Required VRAM7.7 GB
Updated2026-08-02
Maintainercortecs
Model Typemistral
Instruction-BasedYes
Model Files  7.7 GB
GPTQ QuantizationYes
Quantization Typegptq|8bit
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.40.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32768
Torch Data Typefloat16

Best Alternatives to Mistral 7B Instruct V0.3 GPTQ 8B

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB1138811
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB294618
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB265825
Mistral 7B Instruct V0.2 GPTQ32K / 4.2 GB674356
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB140
...tral 7B Instruct 32K GPTQ INT832K / 7.7 GB221
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB60
...stral 7B Instruct V0.3 GPTQ 4B32K / 4.2 GB50
...nstruct V0.2 Neural Story GPTQ32K / 4.6 GB61
Breeze 7B Instruct V0.1 GPTQ32K / 4.7 GB62
Note: green Score (e.g. "73.2") means that the model is better than cortecs/Mistral-7B-Instruct-v0.3-GPTQ-8b.