Can Pixtral 12B run on AMD Instinct MI350X 288GB?

YES — Runs Great

B68Good

Estimated from fit model

Pixtral 12B needs ~39.5 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~168 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 39.5 GB, 168.0 tok/s, Runs well

39.5 GB required288.0 GB available

14% VRAM used

Fit status

Runs well

Decode

168.0 tok/s

TTFT

1152 ms

Safe context

131K

Memory

39.5 GB / 288.0 GB

Memory breakdown

Weights7.3 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsPixtral 12B on AMD Instinct MI350X 288GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.

When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.

Key benefits of running locally:
  - Full privacy: your prompts never leave your machine
  - No per-token cost or rate limits
  - Works offline once the model is downloaded
  - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:

  Model size     Q4 (4-bit)    Q8 (8-bit)    FP16
  7B params      ~4.3 GB       ~7.5 GB       ~14 GB
  13B params     ~7.9 GB       ~13.9 GB      ~26 GB
  70B params     ~42.7 GB      ~74.9 GB      ~140 GB

Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 168.0 tok/s decode · 1.2s TTFT (warm) · 420 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	168.0 tok/s	629 ms	131K
Coding	B	Runs well	168.0 tok/s	1152 ms	131K
Agentic Coding	B	Runs well	168.0 tok/s	1676 ms	131K
Reasoning	B	Runs well	168.0 tok/s	1362 ms	131K
RAG	B	Runs well	168.0 tok/s	2095 ms	131K

Inference speed

Pixtral 12B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Pixtral 12B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~168 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	168.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	112.5	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	101.5	Fits
RTX 3090 24GB	24 GB	Q4_K_M	96.2	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	94.2	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	81.8	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	68.1	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	64.6	Fits
RTX 4070 12GB	12 GB	Q4_K_M	58.3	Offloads
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	44.5	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	44.5	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	35.2	Fits
RTX 3060 12GB	12 GB	Q4_K_M	34.2	Offloads
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	32.3	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	27.2	Fits
RTX 4060 8GB	8 GB	Q4_K_M	9.7	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Pixtral 12B (12B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	4.7 GB	Low	B59
Q3_K_S	3	5.9 GB	Low	B59
NVFP4	4	6.7 GB	Medium	B59
Q4_K_M	4	7.3 GB	Medium	B59
Q5_K_M	5	8.6 GB	High	B59
Q6_K	6	9.8 GB	High	B59
Q8_0	8	12.8 GB	Very High	B60
F16Best for your GPU	16	24.6 GB	Maximum	B61

Get started

Copy-paste commands to run Pixtral 12B on your machine.

Run

ollama run pixtral

Frequently asked questions

Can AMD Instinct MI350X 288GB run Pixtral 12B?

Yes, AMD Instinct MI350X 288GB can run Pixtral 12B with a B grade (Runs well). Expected decode speed: 168.0 tok/s.

How much VRAM does Pixtral 12B need?

Pixtral 12B (12B parameters) requires approximately 39.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Pixtral 12B?

The recommended quantization for Pixtral 12B is Q4_K_M, which balances quality and memory efficiency.

What speed will Pixtral 12B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Pixtral 12B achieves approximately 168.0 tokens per second decode speed with a time-to-first-token of 1152ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Pixtral 12B for coding?

For coding workloads, Pixtral 12B on AMD Instinct MI350X 288GB receives a B grade with 168.0 tok/s and 131K context.

What context window can Pixtral 12B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Pixtral 12B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for Pixtral 12B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/pixtral-12b-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: