whatmodel.sh / Mixtral 8x7B Instruct v0.1

Mixtral 8x7B Instruct v0.1

+ contribute

Mixtral 8x7B Instruct v0.1 is an open-weights language model from Mistral, released December 2023. Its published size is 46.7B parameters (12.9B active per token) and a 32k-token context window. Licence: apache-2.0.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2023-12-11). Exact checkpoint Mixtral-8x7B-Instruct-v0.1 (the API alias open-mixtral-8x7b is a separate Epoch run and is not pooled). 46.7B total / 12.9B per token (Mistral, 'Mixtral of experts'); 46,702,792,704 parameters in safetensors metadata.

40.5±0.5#524 of 719 LLMsfrom 32 benchmark results across 21 sources

$ how it compares

The LLMs ranked either side of Mixtral 8x7B Instruct v0.1, out of 828 with a score, then more from Mistral.

#	model	score	where	RAM	released
614	CodeQwen1.5 7B (base) Alibaba	41±1	local	~6.4GB	2024-04
615	Granite 4.0 1B IBM	41±1	local	~2.4GB	2025-10
616	Mixtral 8x7B Instruct v0.1 Mistral	41±1	local	~29GB	2023-12
617	Molmo 7B-D (0924) Ai2	41±1	local	~35GB	2024-09
618	OpenHermes-2.5-Code-290k-13B ajibawa-2023	41±1	local	~9.8GB	2024-03
	more from Mistral
79	Mistral Large 4 (public preview) Mistral	71±2	api $2.06/M		2026-10
174	Mistral Medium 3.5 (128B) Mistral	65±1	api $3.00/M +local	~42GB	2026-04
180	Mistral Medium 3.1 (2508) Mistral	64±2	comparison only		2025-08

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #277 of 300 * · 0.4% of its score · 1 test

Beats Bielik 11B v2.3 Instruct, Mixtral 8x22B Instruct v0.1, GLM-4 9B Chat here, though they rank higher overall. Trails Granite 4.0 H 350M, Qwen3 0.6B, Qwen2.5 1.5B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
BFCL v3	42.2% ✎	▁▁▁▁▁▃▅█▅▄▁▁ beats 20/114	medium · avg 52%	▇ 0.4%	blunt · at its level

coding▁▁▁▃▆██▇▆▄▃▁ #386 of 458 · 55% of its score · 8 tests

Beats DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B, DeepSeek R1 Distill Llama 8B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Falcon3 3B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
HumanEval +1	45.1% ✎	▁·▁▁▃▄▆▅█▃▁▁ beats 29/99	easy · avg 79%	▇▇▇▇▇▇▇▇▇▇▇ 27%	sharp · at its level · several runs
HumanEval+	39.6% ✎	▁·▁▁▁▃▄▄▄█▃▁ beats 29/99	easy · avg 74%	▇▇▇▇▇ 13%	sharp · at its level
CRUXEval (ZeroEval, 800 problems)	44.9% ✎	▁▂▆▃▆█▆▃▂·▁▁ beats 10/47	medium · avg 61%	▇▇ 4.7%	sharp · at its level
HumanEvalSynthesize (HumanEvalPack, 6-language average)	48.4% ✎	▁·▂▁▂▆▅█▄▄▁▂ beats 27/35	medium · avg 64%	▇ 3.4%	at its level
MBPP+	49.7% ✎	▁···▁▁▂▅▇█▆▂ beats 19/75	easy · avg 68%	▇ 2.3%	at its level
HumanEvalExplain (HumanEvalPack, 6-language average)	37.0% ✎	▄▇█▃▄▇▄▁▇▃·▁ beats 28/35	medium · avg 49%	▇ 2.1%	at its level
HumanEvalFix (HumanEvalPack, 6-language average)	39.3% ✎	▁·▁▁▄██▄█▁▅▅ beats 28/35	medium · avg 56%	▇ 2.0%	sharp · at its level
WebApp1K-React pass@1 (onekq-ai)	12.7% ✎	▃▃▁█▁▄▅▃▄▇▁▄ beats 2/31	medium · avg 44%	▇ 0.4%	sharp · noisy

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #307 of 393 · 12% of its score · 6 tests

Beats Gemma 4 E4B, OpenThinker3 7B, Gemma 4 E2B here, though they rank higher overall. Trails LFM2 350M, Gemma 3 1B, Flan-T5 XXL here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
AlpacaEval 2 length-controlled	23.7% ✎	▁▂▂▃▆▆█▆▄▄▁▁ beats 61/122	medium · avg 39%	▇▇ 4.8%	typical
Arena-Hard (v0.1, GPT-4-1106 judge)	23.4% ✎	▂▁▁▅█▅▄▃▃▅▃▁ beats 21/60	medium · avg 52%	▇ 2.9%	sharp
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)	1114.0 ✎	▂▁▂▁▃▇█▆▇▄▂▂ beats 56/95	avg 1201	▇ 1.8%	blunt
LMArena (text)	1197.1 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 67/379	avg 1268	▇ 1.8%	blunt
AlpacaEval 1.0 win rate (vs text-davinci-003, GPT-4 judge)	94.8% ✎	▂▂·▆·▇▃▆█▆▄▂ beats 41/45	very easy · avg 96%	▇ 0.5%	sharp · noisy
IFEval (aggregation unspecified)	55.1% ✎	▁▁▃▁▂▄▄▆█▃▂▁ beats 18/141	easy · avg 73%	▇ 0.4%	at its level · small run

math▁▂▃▅▆▅▄█▄▁▁▁ #357 of 398 * · 5.7% of its score · 2 tests

Beats Yi 34B Chat, Llama 3 8B Instruct, Command R (03-2024) here, though they rank higher overall. Trails Gemma 3 1B, Stable Code 3B, Qwen3 0.6B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
GSM8K (ZeroEval, zero-shot)	70.1% ✎	▁▄·▃▄█▅▅▅███ beats 4/43	very easy · avg 89%	▇▇ 4.5%	sharp · at its level
MATH level 5	9.3% ✎	▂▃▅▆▄█▆▃▅▂▃▄ beats 5/92	hard · avg 32%	▇ 1.2%	sharp · too hard for it

other tests14 not in a task · 27% of its score

test	result	vs the others in its run	difficulty	counts	why
MMLU-Redux (ZeroEval, 2,778 questions)	63.2% ✎	▁·▁▁▄▄▄▅█▄▂▁ beats 5/53	easy · avg 77%	▇▇▇▇ 9.4%	at its level
EvoEval (overall)	29.3% ✎	▂▂▃▄▄█▁▄▅▃▁▃ beats 14/42	medium · avg 55%	▇▇ 5.1%	at its level
MMLU-Pro	41.9% ✎	▃▂▅█▃·█▃▅··▂ beats 8/23	medium · avg 57%	▇ 2.7%	at its level
WildBench v2 WB-Score (task macro)	31.4703 WB-Score ✎	▁·▁▁·▃█▄▇▆▅▆ beats 18/52	avg 45.199 WB-Score	▇ 2.1%	sharp
CPTUB average (SpeakLeash, 0-5 judge scale)	54.6% ✎	▁▂▂▂▃█▃▆▅▄▂▃ beats 20/95	easy · avg 66%	▇ 1.4%	at its level
BIG-Bench Hard	45.3% ✎	▁▁▁▁▂▄▅▅█▃▄▁ beats 37/129	medium · avg 67%	▇ 1.2%	sharp · at its level · small run
Polish EQ-Bench v2 (SpeakLeash)	58.6% ✎	▁··▁▁▂▂▆▅▆█▆ beats 40/70	medium · avg 64%	▇ 1.1%	at its level
ZebraLogic (ZeroEval, 1,000 puzzles)	8.7% ✎	▁▁▃▆██▁▁·▁▁▁ beats 6/57	hard · avg 18%	▇ 0.9%	sharp · too hard for it

6 more tests

test	result	vs the others in its run	difficulty	counts	why
GPQA Diamond	30.6% ✎	▁▁▁▁▃▄▆▄▅▇█▅ beats 17/208	hard · avg 40%	▇ 0.8%	sharp · too hard for it
Open Persian LLM Leaderboard v2 average (21 tasks)	46.1% ✎	▂▄▂▃█▄▃▆▃▅▂▂ beats 20/81	medium · avg 58%	▇ 0.8%	blunt · at its level
KINA (Knowledge Index of Noah's Ark) accuracy, 899 ten-option items	17.8% ✎	▁▁▃▁▃▄█▆▄▅▂▃ beats 2/39	very hard · avg 22%	▇ 0.5%	blunt
Open PT-LLM Leaderboard average (9 Portuguese tasks)	73.1% ✎	▃▁▁▁▁▁▁▁▂█▅▁ beats 205/276	medium · avg 73%	▇ 0.4%	at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy	87.3% ✎	▁▁▁▁▁▁▁▂▄█▄▃ beats 106/146	easy · avg 83%	▇ 0.3%	at its level · noisy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)	79.9% ✎	▁▃▂▃▄▄█▆▃▂▂▁ beats 5/140	very easy · avg 94%	▇ 0.2%	blunt · noisy

$ where to run it

llama.cpp · recommended

version

Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
macOS / Linux
curl -LsSf https://llama.app/install.sh | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run Mixtral 8x7B Instruct v0.1 · needs ~26.4 GB · from huggingface.co/TheBloke
chat in the terminal
llama cli -hf TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Mixtral 8x7B Instruct v0.1 · needs ~26.4 GB · from huggingface.co/TheBloke
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Mixtral 8x7B Instruct v0.1 · needs ~28.52 GB · from ollama.com
chat in the terminal
ollama run mixtral:8x7b

MLX (Mac)

version

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run Mixtral 8x7B Instruct v0.1 · needs ~26.3 GB, Mac only · from huggingface.co/mlx-community
chat in the terminal
mlx_lm.chat --model mlx-community/Mixtral-8x7B-Instruct-v0.1-4bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/Mixtral-8x7B-Instruct-v0.1-4bit

Weights and documentation: huggingface.co/mistralai ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 33%, WildEval ZeroEval published r… 20%, Top Leaderboard Ranking = Top… 15% and 18 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
EvalPlus / EvalPerf published evaluation runs	3	▇▇▇▇▇▇▇▇▇▇ 33%	Apache-2.0
WildEval ZeroEval published results	4	▇▇▇▇▇▇ 20%	Apache-2.0
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs	2	▇▇▇▇ 15%	CC BY 4.0
Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runs	3	▇▇ 8%	CC BY 4.0
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)	2	▇▇ 5%	Apache-2.0
Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)	1	▇ 3%	Apache-2.0
MMLU-Pro author-released evaluation runs	1	▇ 3%	Apache-2.0
WildBench v2 leaderboard data (Ai2)	1	▇ 2%	Apache-2.0
Epoch AI — internal evaluations	2	▇ 2%	CC BY 4.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)	1	▇ 2%	CC-BY-4.0
LMArena leaderboard dataset	1	▇ 2%	CC BY 4.0
HuggingFaceH4 zephyr-orpo-141b-A35b-v0.1 model card	2	▇ 2%	Apache-2.0
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)	1	▇ 1%	MIT
SpeakLeash Polish EQ-Bench leaderboard	1	▇ 1%	Apache-2.0
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)	1	▇ 1%	Apache-2.0
Knowledge Index of Noah's Ark (arXiv:2606.05104v2)	1	▇ 0%	CC BY 4.0
WebApp1K models leaderboard (onekq-ai)	1	▇ 0%	MIT
Berkeley Function Calling Leaderboard result archive	1	▇ 0%	Apache-2.0
Open Portuguese LLM Leaderboard (archived)	1	▇ 0%	Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard	1	▇ 0%	MIT
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)	1	▇ 0%	Apache-2.0
prior · pull toward the middle		▇ 0%
weighted average		= 40.5