LLM EXPLORER 60,783 MODELS INDEXED

Mixtral 8x7B Instruct V0.1 by mistralai

By mistralai · 842893 downloads
HF Repo ↗ Copy URL

Mixtral 8x7B Instruct V0.1 is an open-source language model by mistralai. Features: 46.7b LLM, VRAM: 93.6GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.46, ELO: 1197, Arc: 90.3, HellaSwag: 80.3, MMLU: 68.7, GSM8K: 71.7.

Base model:finetune:mistralai/... Base model:mistralai/mixtral-8...   De   En   Es   Eval-results   Fr   Instruct   It   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1 

Mixtral 8x7B Instruct V0.1 Benchmarks

LMSys ELO 1197 vs 1272 (so35) -5.9%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Mixtral 8x7B Instruct V0.1 Parameters and Internals

Model Type 
pretrained generative Sparse Mixture of Experts
Additional Notes 
The Mixtral-8x7B Instruct model can be easily fine-tuned and does not have any moderation mechanisms.
Supported Languages 
fr (French), it (Italian), de (German), es (Spanish), en (English)
LLM NameMixtral 8x7B Instruct V0.1
Repository 🤗https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1 
Base Model(s)  mistralai/Mixtral-8x7B-v0.1   mistralai/Mixtral-8x7B-v0.1
Model Size46.7b
Required VRAM93.6 GB
Updated2026-08-06
Maintainermistralai
Model Typemixtral
Instruction-BasedYes
Model Files  12.1 GB   12.1 GB   12.1 GB   12.1 GB   12.1 GB   12.1 GB   12.1 GB   12.1 GB   4.9 GB: 1-of-19   5.0 GB: 2-of-19   5.0 GB: 3-of-19   4.9 GB: 4-of-19   5.0 GB: 5-of-19   5.0 GB: 6-of-19   4.9 GB: 7-of-19   5.0 GB: 8-of-19   5.0 GB: 9-of-19   4.9 GB: 10-of-19   5.0 GB: 11-of-19   5.0 GB: 12-of-19   5.0 GB: 13-of-19   4.9 GB: 14-of-19   5.0 GB: 15-of-19   5.0 GB: 16-of-19   4.9 GB: 17-of-19   5.0 GB: 18-of-19   4.2 GB: 19-of-19
Supported Languagesfr it de es en
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Mixtral 8x7B Instruct V0.1

Model
Likes
Downloads
VRAM
...ixtral 8x7B Instruct V0.1 GGUF6551849115 GB
...ixtral 8x7B Instruct V0.1 GGUF259717 GB
Mixtral 8x7B Instruct V0.1 AWQ59104524 GB
...ixtral 8x7B Instruct V0.1 GGUF550717 GB
...ixtral 8x7B Instruct V0.1 GPTQ14121023 GB
Notux 8x7b V1.3.5bpw EXL22820 GB
Notux 8x7b V1.3.5bpw H6 EXL21620 GB
...es Mixtral 8x7B 2.4bpw H6 EXL22714 GB
...es Mixtral 8x7B 3.0bpw H6 EXL21917 GB
...es Mixtral 8x7B 6.0bpw H6 EXL21735 GB

Best Alternatives to Mixtral 8x7B Instruct V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB70
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB33830
Merge Mixtral Prometheus 8x7B32K / 91.9 GB122
...xtral 8x7B Yes Instruct LimaRP32K / 93.5 GB51
Notux 8x7b V132K / 93.6 GB43165
BagelMIsteryTour V2 8x7B32K / 93.5 GB9417
...rkrautLM Mixtral 8x7B Instruct32K / 93.6 GB8422
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB3740
Sage Ft Mixtral 8x7b32K / 90 GB4525
Dolphin 2.5 Mixtral 8x7b32K / 93.6 GB41251235