Skip to content

Pixtral 12B on RTX 4060: VRAM, speed and fit

Pixtral 12B at 4-bit needs 9.3 GB; the RTX 4060 can use 8.0 GB. The smallest machine we checked that runs it is the RTX PRO 2000 Blackwell.

Text generation · Chat · Ollama / LM Studio

Won’t fit · on RTX 4060 · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat

GPU memory
9.3 GB
of 8.0 GB
Context
8K
auto
Speed
n/a
First reply
n/a

Where the memory goes

Model
7.2 GB
Context
1.3 GB
Overhead
877 MB
OS
0.0 GB
Over by
1.3 GB
Memory
9.3 GB of 8.0 GB
Context
8K tokens · auto
Speed
Doesn’t run here
Running cost
Doesn’t run here · $29/mo on a cloud RTX 2000 Ada

Validation: Not validated

What Pixtral 12B on RTX 4060 was checked against
CheckTargetResultStatus
Fits in GPU memory8.0 GB usable9.3 GB neededFails
Headroom5% freenoneFails
Context for chat16K or more–Not run
Writing speed15 tok/s or more–Not run
First replyunder 3 s, 2K prompt–Not run

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Pixtral 12B
Parameters
12.7B
Precision
4-bit (Q4_K_M)
Context
8K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 4060
GPU can use
8.0 GB of 8.0 GB

Worth trying

  • 2× RTX 4060: Fits across the cards, 40K context
  • Spill to RAM: Runs, slower, 18 tok/s
  • RTX PRO 2000 Blackwell: Runs it with 44K context
  • M5 Max · 36 GB: Runs it with 88K context

Running cost

At home
n/a
Doesn’t run on this machine.
Renting instead
$29/mo
RTX 2000 Ada at $0.24/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf ggml-org/pixtral-12b-GGUF
vLLM
vllm serve mistral-experimental/pixtral-12b

Pixtral 12B on similar machines

All machines: Pixtral 12B VRAM requirements. Everything that runs here: what can the RTX 4060 run?

Other models that run on RTX 4060

Questions

Can Pixtral 12B run on RTX 4060?

Pixtral 12B at 4-bit needs 9.3 GB; the RTX 4060 can use 8.0 GB. The smallest machine we checked that runs it is the RTX PRO 2000 Blackwell.

Shown at the closest setup. Report VR-14YL5BI, calculated Nov 22, 2026 from published specs, not benchmarked.