FitMyLLM
Mistral AI/Dense

Mistral AIPixtral 12B

Pixtral 12B — Mistral's first vision model. Understands images and code.

visionchatcodingThinking
12B
Parameters
128K
Context length
9
Benchmarks
10
Quantizations
380K
HF downloads
Architecture
Dense
Released
2024-09-17
Layers
40
KV Heads
8
Head Dim
128
Family
mistral

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q3_K_M4
8.4 GB
6.5 + 1.9 KV
low
Q3_K_L4.3
8.8 GB
6.9 + 1.9 KV
moderate
IQ4_XS4.46
9.1 GB
7.2 + 1.9 KV
moderate
Q4_K_S4.67
9.4 GB
7.5 + 1.9 KV
moderate
Q4_K_M4.89
9.7 GB
7.8 + 1.9 KV
good
Q5_K_S5.57
10.7 GB
8.8 + 1.9 KV
good
Q5_K_M5.7
10.9 GB
9.0 + 1.9 KV
good
Q6_K6.56
12.2 GB
10.3 + 1.9 KV
excellent
Q8_08.5
15.1 GB
13.2 + 1.9 KV
lossless
FP1616
26.4 GB
24.5 + 1.9 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN PIXTRAL 12B NOW

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (9)

MMBench78.0
IFEval72.0
MMLU-PRO58.0
BBH58.0
MMMU52.5
HumanEval52.0
MATH42.0
GPQA38.0
MUSR18.0

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run mistral:12b-q4_K_M

Tag may need adjustment — check ollama.com/library/mistral for available tags.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M1 (8GB)
8 GB VRAM • 68 GB/s
APPLE
$499
Apple M2 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
Apple M3 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
NVIDIA Tesla K8
8 GB VRAM • 160 GB/s
NVIDIA
NVIDIA Tesla M60
8 GB VRAM • 160 GB/s
NVIDIA

Find the best GPU for Pixtral 12B

Build Hardware for Pixtral 12B

Pixtral 12B — Mistral's first vision model. Understands images and code.

▸ SPEC SHEET

Pixtral 12B12B Dense.

▸ SPECIFICATIONS
PARAMETERS
12B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
128K tokens
CAPABILITIES
vision, chat, coding
RELEASE DATE
2024-09-17
PROVIDER
Mistral AI
FAMILY
mistral
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q3_K_M46.5 GB88%
Q3_K_L4.36.9 GB90%
IQ4_XS4.467.2 GB92%
Q4_K_S4.677.5 GB93%
Q4_K_M4.897.8 GB94%
Q5_K_S5.578.8 GB96%
Q5_K_M5.79.0 GB96%
Q6_K6.5610.3 GB97%
Q8_08.513.2 GB100%
FP161624.5 GB100%
§ 01BENCHMARK SCORES
HumanEval52.0
MMLU-PRO58.0
MATH42.0
IFEval72.0
BBH58.0
MMMU52.5
GPQA38.0
MUSR18.0
MMBench78.0
§ 02RUN COMMAND

Run Pixtral 12B locally with Ollama — needs 7.8 GB VRAM at Q4_K_M:

$ollama run pixtral:12b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M