Mistral AIMixtralMixtralForCausalLM

Mixtral 8x7B v0.1 — Hardware Requirements & GPU Compatibility

Chat

Mixtral-8x7B-v0.1 is Mistral AI's pretrained Sparse Mixture-of-Experts model, combining eight 7-billion-parameter experts for roughly 46.7 billion total parameters. As a base checkpoint, it has no built-in moderation or instruction-following behavior and is intended as a foundation for further fine-tuning rather than direct chat use. It supports a 32K token context window and is released under the Apache 2.0 license, allowing unrestricted commercial and research use. At around 47 billion total parameters, running it locally at 4-bit quantization needs roughly 24-32 GB of memory, putting it within reach of a single high-end consumer GPU or a dual-GPU setup.

46.7B params · MoE13B active33K contextApache 2.0Dec 202334.8K downloads1.8K likes15.4K quant downloads

Your hardware

Verdicts below are for the reference RTX 4090. Set yours to personalise the page.

Detection reads your browser's GPU name with no data sent anywhere.

C

Usable on a 24 GB GPU

Runs from 16 GB (IQ2_XXS · 16K)Best on 24 GB (IQ3_M · ~92 tok/s · 16K)Macs from 24 GB (IQ2_M · ~37 tok/s)

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Mixtral 8x7B v0.1

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama

one command · needs Ollama installed

$ollama run hf.co/TheBloke/Mixtral-8x7B-v0.1-GGUF:Q4_K_M

Q4_K_M · needs ~30.5 GB · 16K context

Download: mixtral-8x7b-v0.1.Q4_K_M.gguf26.44 GBTheBloke

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 48 GB GPU

The easiest way to try this model
Running in a few minutes, easy setup
Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does Mixtral 8x7B v0.1 Need?

Select a quantization level; the listed hardware adheres to it.

Quantization	VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
	13.4 GB	17.4 GB	—	12.5 GB	2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss	Fits: 32K context · ~135 tok/s
	14.6 GB	18.6 GB	—	13.8 GB	2-bit · i-quant extra small — Importance-weighted 2-bit, extra small	Fits: 32K context · ~127 tok/s
	15.2 GB	19.2 GB	—	14.3 GB	2-bit · i-quant small — Importance-weighted 2-bit, small	Fits: 32K context · ~123 tok/s
	16.3 GB	20.4 GB	—	15.7 GB	2-bit · i-quant medium — Importance-weighted 2-bit, medium	Fits: 32K context · ~116 tok/s
	18.7 GB	22.7 GB	—	18.5 GB	3-bit · i-quant — Importance-weighted 3-bit	Fits: 32K context · ~104 tok/s
	19.8 GB	23.9 GB	—	19.4 GB	3-bit · i-quant extra small — Importance-weighted 3-bit, extra small	Fits: 32K context · ~99 tok/s
	20.4 GB	24.5 GB	—	15.6 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 16K context · ~97 tok/s
	20.4 GB	24.5 GB	—	20.6 GB	3-bit · i-quant small — Importance-weighted 3-bit, small	Fits: 16K context · ~97 tok/s
	21 GB	25 GB	—	20.6 GB	3-bit small — 3-bit small quantization	Fits: 16K context · ~94 tok/s
	21.6 GB	25.6 GB	—	21.6 GB	3-bit · i-quant medium — Importance-weighted 3-bit, medium	Fits: 16K context · ~92 tok/s
	23.3 GB	27.4 GB	—	20.4 GB	3-bit medium — 3-bit medium quantization	Fits: 4K context · ~86 tok/s
	23.9 GB	28 GB	—	26.4 GB	4-bit · legacy — 4-bit legacy quantization	Fits: 2K context · ~85 tok/s
	24.5 GB	28.5 GB	—	24.3 GB	3-bit large — 3-bit large quantization	Does not fit: needs 26.4 GB
	25.7 GB	29.7 GB	—	25.2 GB	4-bit · i-quant compact — Importance-weighted 4-bit, compact	Does not fit: needs 27.6 GB
	26.8 GB	30.9 GB	—	26.7 GB	4-bit · i-quant non-linear — Importance-weighted 4-bit, non-linear	Does not fit: needs 28.7 GB
	26.8 GB	30.9 GB	—	26.9 GB	4-bit small — 4-bit small quantization	Does not fit: needs 28.7 GB
	28.6 GB	32.6 GB	—	26.4 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Does not fit: needs 30.5 GB
	29.8 GB	33.8 GB	—	32.2 GB	5-bit · legacy — 5-bit legacy quantization	Does not fit: needs 31.6 GB
	32.7 GB	36.7 GB	—	32.4 GB	5-bit small — 5-bit small quantization	Does not fit: needs 34.6 GB
	33.8 GB	37.9 GB	—	32.2 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Does not fit: needs 35.7 GB
	39.1 GB	43.1 GB	—	38.4 GB	6-bit, very good — 6-bit quantization, very good quality	Does not fit: needs 41 GB
	47.3 GB	51.3 GB	—	49.6 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Does not fit: needs 49.2 GB
	94.0 GB	98 GB	—	~93.4 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 95.9 GB

est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

30.5GBat 16K context

Weights: 28.0 GB
KV cache: 2.2 GB
Overhead: 0.3 GB

Doesn't fit RTX 4090 (reference) · needs 6.5 GB more, IQ3_M fits

≥50 tok/s needs ≥664 GB/s · RTX 5090 ~117

Or .

Which Hardware Can Run Mixtral 8x7B v0.1?

Q4_K_M · 28.6 GB

Mixtral 8x7B v0.1 (Q4_K_M) requires 28.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 38+ GB is recommended. Using the full 33K context window can add up to 4.0 GB, bringing total usage to 32.6 GB. 1 GPU can run it, including NVIDIA GeForce RTX 5090. 78 devices with unified memory can run Mixtral 8x7B v0.1, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Max (36 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8–12 GB · RTX 4060, RTX 3060 12GBDoesn't fit — smallest quant needs 15.3 GB8 GB tier →12 GB tier →

16 GB · RTX 5060 Ti 16GBIQ2_XXS · 15.3 GB · ~69 tok/s · 16K15.3~6916K16 GB tier →

24 GB · RTX 4090referenceIQ3_M · 23.5 GB · ~92 tok/s · 16K23.5~9216K24 GB tier →

Mac 32 GB · Mac Mini M4IQ4_XS · 27.6 GB · ~11 tok/s · 16K27.6~1116KMacs →

Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 30.5 GB · ~37 tok/s · 32K30.5~3732KMacs →

How good is Mixtral 8x7B v0.1?

llmrun Score blends public benchmark boards into one number; 100 = the average open model.

Not enough data yet for an llmrun Score.

A Score needs results on enough independent boards. How the Composite Score is built

Benchmarks

MMLU-Pro
TIGER-LabIndependent
41.0%
#99/146 open
Independent
MMLU
Epoch AI · Dec 2023Lab-reported
70.6%
#26/85 open
Lab-reported
GSM8K
Epoch AI · Dec 2023Lab-reported
74.4%
#17/62 open
Lab-reported
HellaSwag
Epoch AI · Dec 2023Lab-reported
86.7%
#5/47 open
Lab-reported
ARC Challenge
Epoch AI · Dec 2023Lab-reported
87.3%
#7/56 open
Lab-reported
WinoGrande
Epoch AI · Dec 2023Lab-reported
77.2%
#14/51 open
Lab-reported

All 9 Mixtral 8x7B v0.1 benchmarks

Alternatives to Mixtral 8x7B v0.1

Mixtral family · 7 models →

Similar models

3tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Kimi Linear 48B A3B BaseMoonshot AI	—	23.4 GB	~275	same size
Llama 3 3 Nemotron Super 49B V1 5NVIDIA	—	22.8 GB	~35	same size
Nemotron H 47B Reasoning 128KNVIDIA	—	107.2 GB	—needs > 24 GB	same size

Fine-tunes & variants(3)community builds of Mixtral 8x7B v0.1

Specifications

Publisher: Mistral AI
Family: Mixtral
Parameters: 46.7B
Active parameters: 12.9B per token
Architecture: MixtralForCausalLM
Context Length: 32,768 tokens
Vocabulary Size: 32,000
Release Date: 2023-12-01
License: Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does Mixtral 8x7B v0.1 need?

Mixtral 8x7B v0.1 requires 28.6 GB of VRAM at Q4_K_M, or 94.0 GB at BF16. Full 33K context adds up to 4.0 GB (32.6 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 46.7B × 4.8 bits ÷ 8 = 28 GB

KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 4.6 GB (at full 33K context)

VRAM usage by quantization

Q4_K_M

28.6 GB

Q4_K_M + full context

32.6 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Mixtral 8x7B v0.1?

Yes, at Q4_0 (23.9 GB) or lower. Higher quantizations like Q3_K_L (24.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Mixtral 8x7B v0.1?

For Mixtral 8x7B v0.1, Q4_K_M (28.6 GB) offers the best balance of quality and VRAM usage. Q5_0 (29.8 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 13.4 GB.

VRAM requirement by quantization

IQ2_XXS

13.4 GB~53%

Q2_K

20.4 GB~75%

Q4_0

23.9 GB~85%

Q4_K_M ★

28.6 GB~89%

Q5_0

29.8 GB~90%

BF16

94.0 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Mixtral 8x7B v0.1 on a Mac?

Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Mixtral 8x7B v0.1, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 28.6 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M5 Max (36 GB).

Can I run Mixtral 8x7B v0.1 locally?

Yes — Mixtral 8x7B v0.1 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Mixtral 8x7B v0.1?

At Q4_K_M, Mixtral 8x7B v0.1 can reach ~124 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)

Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.

Example: NVIDIA B200 → 7.9 GB active ÷ (8000 × 0.65) = 1.52 ms, plus 32 layers × 0.055 ms = 1.76 ms, so 1000 ÷ 3.28 ms = ~305 tok/s

Estimated speed at Q4_K_M (28.6 GB)

NVIDIA B200

~305 tok/s

NVIDIA B300

~305 tok/s

NVIDIA GH200 Grace Hopper Superchip

~236 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Mixtral 8x7B v0.1?

At Q4_K_M, the download is about 28.02 GB. The full-precision BF16 version is 93.41 GB. The smallest option (IQ2_XXS) is 12.84 GB.

Which GPUs can run Mixtral 8x7B v0.1?

1 consumer GPU can run Mixtral 8x7B v0.1 at Q4_K_M. Top options include NVIDIA GeForce RTX 5090.

Which devices can run Mixtral 8x7B v0.1?

78 devices with unified memory can run Mixtral 8x7B v0.1 at Q4_K_M (28.6 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.

Run Mixtral 8x7B v0.1

30.5 GB VRAM at 16K context

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run hf.co/TheBloke/Mixtral-8x7B-v0.1-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=16384 ollama serve.
$/set parameter num_ctx 16384
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 16384. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf TheBloke/Mixtral-8x7B-v0.1-GGUF:Q4_K_M -c 16384 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Option A: Docker Model Runner
Docker Desktop: Settings > AI > Enable Docker Model Runner. Docker Engine on Linux: install the docker-model-plugin package.
$docker model run hf.co/TheBloke/Mixtral-8x7B-v0.1-GGUF:Q4_K_M
Model Runner docs ↗
The quant tag after the repo is how Hugging Face cards write it; if your Docker version rejects it, drop the tag and pick the quant by repo.
Option B: llama.cpp server image (NVIDIA)
Needs the NVIDIA Container Toolkit. Models are cached in the llama-cache volume. Open http://localhost:8080.
$docker run --gpus all -p 8080:8080 -v llama-cache:/root/.cache ghcr.io/ggml-org/llama.cpp:server-cuda -hf TheBloke/Mixtral-8x7B-v0.1-GGUF:Q4_K_M -c 16384 -ngl 99 --host 0.0.0.0 --port 8080
Image tags (cuda13, vulkan, rocm) ↗
Cache path inside the image is not in the docs; remove the -v flag if the volume complains.

Linux only.

Install vLLM
Linux only; on Windows run it inside WSL2. NVIDIA GPU shown; AMD ROCm, Intel and CPU builds have their own install pages.
$uv venv --python 3.12 --seed
$source .venv/bin/activate
$uv pip install vllm --torch-backend=auto
vLLM installation ↗
Serve the model
OpenAI-compatible API at http://localhost:8000/v1.
$vllm serve mistralai/Mixtral-8x7B-v0.1 --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~103 GB of GPU memory.

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$TheBloke/Mixtral-8x7B-v0.1-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
A100 40GBCheapestCheapest9 GB free	~105 tok/s	$1.62	Deploy on Vast.aifrom $0.61/hr (opens in new tab)	9 GB free · ~105 tok/s · $1.62 / 1M tokens
A40 (48 GB)17 GB free	~52 tok/s	$1.87	Deploy on RunPodfrom $0.35/hr (opens in new tab)	48 GB · 17 GB free · ~52 tok/s · $1.87 / 1M tokens
RTX A6000 (48 GB)17 GB free	~57 tok/s	$1.97	Deploy on Vast.aifrom $0.40/hr (opens in new tab)	48 GB · 17 GB free · ~57 tok/s · $1.97 / 1M tokens
A40 (48 GB)17 GB free	~52 tok/s	$3.50	Deploy on Vast.aifrom $0.66/hr (opens in new tab)	48 GB · 17 GB free · ~52 tok/s · $3.50 / 1M tokens
RTX 6000 Ada (48 GB)17 GB free	~70 tok/s	$2.67	Deploy on Vast.aifrom $0.67/hr (opens in new tab)	48 GB · 17 GB free · ~70 tok/s · $2.67 / 1M tokens
L40 (48 GB)17 GB free	~63 tok/s	$3.03	Deploy on RunPodfrom $0.69/hr (opens in new tab)	48 GB · 17 GB free · ~63 tok/s · $3.03 / 1M tokens
RTX 6000 Ada (48 GB)17 GB free	~70 tok/s	$2.96	Deploy on RunPodfrom $0.74/hr (opens in new tab)	48 GB · 17 GB free · ~70 tok/s · $2.96 / 1M tokens
L40S (48 GB)17 GB free	~63 tok/s	$3.47	Deploy on RunPodfrom $0.79/hr (opens in new tab)	48 GB · 17 GB free · ~63 tok/s · $3.47 / 1M tokens

Compare GPUs →

Your own private copy of Mixtral 8x7B v0.1 · Q4_K_M · OpenAI-compatible API

Use it

Copy the endpoint URL from its page on RunPod (any of its links works) and paste it with the key. Both stay in this browser.

Endpoint URL

API key

Chats and keys stay only in this browser.

https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1

Put your endpoint ID in place of <ENDPOINT_ID>. The API key is the one from step 2.

from openai import OpenAI
client = OpenAI(base_url="https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1", api_key="rpa_...")
r = client.chat.completions.create(
    model="any",
    messages=[{"role": "user", "content": "Hello!"}])
print(r.choices[0].message.content)

Works with any OpenAI client.

https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1

Put your endpoint ID in place of <ENDPOINT_ID>. The API key is the one from step 2.

Free on Windows, macOS, Linux, iOS, Android and the web.

Open the web app ↗ (opens in a new tab)Download ↗ (opens in a new tab)

1. Settings → Model Provider → Add → Add Custom Provider
2. API Mode OpenAI API Compatible; paste the API key and the base URL as API Host
3. Model → Fetch, pick the model
4. New chat → pick the provider → start chatting

Free and open source for Windows, macOS and Linux.

Download Jan ↗ (opens in a new tab)

1.Settings → next to Model Providers press +
2.API format OpenAI-compatible; Base URL is the base URL above (with /v1); API key is your key; Create
3.If no model appears, click + in Models and type any
4.New chat → pick the model → start chatting