llmrun
Mistral AIMixtralMixtralForCausalLM

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

Chat

Mixtral 8x7B Instruct v0.1 is Mistral AI's flagship Mixture-of-Experts model, combining eight expert networks of 7 billion parameters each for a 46.7B total weight count while activating only about 12.9 billion parameters per token. This sparse architecture delivers performance that rivals much larger dense models at a fraction of the inference cost, excelling across reasoning, code generation, and multilingual tasks. Because the full weights must still be loaded into memory, you will need around 24–48 GB of VRAM depending on quantization level, making it best suited for multi-GPU desktop setups or high-VRAM workstation cards. If your hardware can accommodate it, Mixtral offers one of the best performance-per-active-parameter ratios available for local deployment.

46.7B params · MoE13B active33K contextApache 2.0292.7K downloads4.8K likes38.3K quant downloads
Based on Mixtral 8x7B v0.1
C

Usable on a 24 GB GPU

Runs from16 GB IQ2_XXS · 16KBest on24 GB IQ3_M · ~92 tok/s · 16KMacs from24 GB IQ2_M · ~37 tok/s

Score 65.8#100 of 106 open#31 of 36 that fit 24 GBApache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

llmrun Composite Score →

65.8

Benchmarks · tier chart ↓
Among 106 open modelsHow the Composite Score is built

Run Mixtral 8x7B Instruct 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 mixtral:8x7b-instruct-v0.1-q4_K_M

Q4_K_M · needs ~30.5 GB · 16K context

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

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on A100 40GB (9 GB headroom) · Q4_K_M

Generation speed
~105 tok/s
generation speed
Cost per 1M output tokens
$1.07
per 1M output tokens
Deployon Vast.aiBest valuefrom $0.40/hr (opens in new tab)
Compare GPUs →
or

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

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

QuantizationVRAM+32KOn RTX 4090 (reference)
20.4 GB24.5 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 16K context · ~97 tok/s
21 GB25 GB3-bit small — 3-bit small quantizationFits: 16K context · ~94 tok/s
23.3 GB27.4 GB3-bit medium — 3-bit medium quantizationFits: 4K context · ~86 tok/s
23.9 GB28 GB4-bit · legacy — 4-bit legacy quantizationFits: 2K context · ~85 tok/s
28.6 GB32.6 GB4-bit medium — 4-bit medium quantization — most popular sweet spotDoes not fit: needs 30.5 GB
33.8 GB37.9 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffDoes not fit: needs 35.7 GB
39.1 GB43.1 GB6-bit, very good — 6-bit quantization, very good qualityDoes not fit: needs 41 GB
47.3 GB51.3 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 49.2 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 Instruct v0.1?

Q4_K_M · 28.6 GB

Mixtral 8x7B Instruct 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 Instruct 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
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 · 16K16 GB tier →
24 GB · RTX 4090referenceIQ3_M · 23.5 GB · ~92 tok/s · 16K24 GB tier →
Mac 32 GB · Mac Mini M4IQ4_XS · 27.6 GB · ~11 tok/s · 16KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 30.5 GB · ~37 tok/s · 32KMacs →

How good is Mixtral 8x7B Instruct v0.1?

The llmrun Score merges 4 public benchmark boards into a single figure, where 100 represents the average for open models.

Score vs VRAM in the 24 GB tier

  • Mixtral 8x7B Instruct v0.1
  • Other models
  • Best Score for its VRAM

#31 of 36 that fit 24 GB

Each dot is a model at the best quant that fits a 24 GB GPU. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.

Full 24 GB ranking →

Benchmarks

Here are all 6 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.

  • GPQA Diamond

    Epoch AI · Dec 2023Independent

    30.6%

    #83/100 open

    Independent
  • LMArena Text

    LMArena · Oct 2026Arena

    1197.2

    #148/188 open

    Arena
  • MMLU-Pro

    TIGER-LabIndependent

    43.3%

    #93/146 open

    Independent
  • MATH Level 5

    Epoch AI · Dec 2023Independent

    10.0%

    #34/39 open

    Independent
  • DTBench

    Epoch AI · Dec 2023Lab-reported

    49.6%

    #62/70 open

    Lab-reported
  • ForecastBench

    Epoch AI · Dec 2023Lab-reported

    58.2

    #23/24 open

    Lab-reported
All 6 Mixtral 8x7B Instruct v0.1 benchmarks

In the 24 GB class

36 models fit 24 GB

Same Score, only models that fit 24 GB at their best quant: the ranking a 24 GB owner actually chooses from.

  1. #1

    Qwen3.8 27BAlibaba

    122.0

    ~38 tok/s · 17.9 GB

  2. #2

    Qwen3.6 27BAlibaba

    111.2

    ~38 tok/s · 17.9 GB

  3. #3

    Qwen3.6 35B A3BAlibaba

    106.8

    ~151 tok/s · 22.0 GB

  4. #4

    Gemma 4 31B ITGoogle

    106.7

    ~32 tok/s · 21.7 GB

  5. #5

    Gemma 4 26B A4B ITGoogle

    105.8

    ~171 tok/s · 16.5 GB

  6. #6

    Qwen3.5 35B A3BAlibaba

    105.8

    ~151 tok/s · 22.0 GB

Full 24 GB ranking →RTX 4090 page →

Alternatives to Mixtral 8x7B Instruct v0.1

Mixtral family · 7 models →

Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.

Similar models

10
ModelScoreVRAMtok/sWhy it is similar
Gemma 4 31B ITGoogle106.721.7 GB~32similar score
Gemma 4 26B A4B ITGoogle105.816.5 GB~171similar score
Qwen3.5 35B A3BAlibaba105.822 GB~151similar score
Qwen3.5 27BAlibaba103.817.9 GB~38similar score
Seed OSS 36B InstructByteDance-Seed102.522.8 GB~31similar score
Qwen3 30B A3B Thinking 2507Alibaba100.719.4 GB~173similar score
Mistral Nemo Instruct 2407Mistral AI65.411 GB~81similar score
Qwen2.5 7B InstructAlibaba65.15.8 GB~131similar score
Gemma 3 4B ITGoogle64.05 GB~231similar score
DeepSeek R1 Distill Qwen 32BDeepSeek97.223 GB~34same size

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
2023-12-10
License
Apache 2.0

Resources

Frequently Asked Questions

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

Mixtral 8x7B Instruct 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

28.6 GB
32.6 GB

Learn more about VRAM estimation →

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

For Mixtral 8x7B Instruct 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
IQ3_XS
19.8 GB
Q3_K_L
24.5 GB
Q4_K_M ★
28.6 GB
Q5_0
29.8 GB
BF16
94.0 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

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

Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Mixtral 8x7B Instruct 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 Instruct v0.1 locally?

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

How fast is Mixtral 8x7B Instruct v0.1?

At Q4_K_M, Mixtral 8x7B Instruct 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)

~305 tok/s
~305 tok/s
~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 Instruct 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 Instruct v0.1?

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

Which devices can run Mixtral 8x7B Instruct v0.1?

78 devices with unified memory can run Mixtral 8x7B Instruct 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.