Can Mistral Small 24B Instruct 2501 run on AMD Instinct MI350X 288GB?

YES — Runs Great

C45Usable

Estimated from fit model

Mistral Small 24B Instruct 2501 needs ~47.2 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~336 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) — 47.2 GB, 336.0 tok/s, Runs well

47.2 GB required288.0 GB available

16% VRAM used

Fit status

Runs well

Decode

336.0 tok/s

TTFT

576 ms

Safe context

1.4M

Memory

47.2 GB / 288.0 GB

Memory breakdown

Weights14.6 GB

KV Cache2.8 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsMistral Small 24B Instruct 2501 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: 336.0 tok/s decode · 576ms TTFT (warm) · 840 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	C	Runs well	336.0 tok/s	350 ms	1.4M
Coding	C	Runs well	336.0 tok/s	576 ms	1.4M
Agentic Coding	C	Runs well	336.0 tok/s	838 ms	1.4M
Reasoning	C	Runs well	336.0 tok/s	681 ms	1.4M
RAG	C	Runs well	336.0 tok/s	1048 ms	1.4M

Inference speed

Mistral Small 24B Instruct 2501 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Mistral Small 24B Instruct 2501 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~82 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	82.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	52.3	Tight
RX 7900 XTX 24GB	24 GB	Q4_K_M	47.2	Tight
RTX 3090 24GB	24 GB	Q4_K_M	44.8	Tight
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	38.0	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	34.2	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	34.2	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	31.7	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	30.1	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	21.5	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	19.1	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	16.4	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	15.0	Fits
RTX 4070 12GB	12 GB	Q4_K_M	6.7	Too big
RTX 3060 12GB	12 GB	Q4_K_M	4.2	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	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 Mistral Small 24B Instruct 2501 (24B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	D36
Q3_K_S	3	11.8 GB	Low	D36
NVFP4	4	13.4 GB	Medium	D36
Q4_K_M	4	14.6 GB	Medium	D36
Q5_K_M	5	17.3 GB	High	D36
Q6_K	6	19.7 GB	High	D37
Q8_0	8	25.7 GB	Very High	D37
F16Best for your GPU	16	49.2 GB	Maximum	D39

Get started

Copy-paste commands to run Mistral Small 24B Instruct 2501 on your machine.

Run

lms load hf-maziyarpanahi--mistral-small-24b-instruct-2501-gguf && lms server start

Frequently asked questions

Can AMD Instinct MI350X 288GB run Mistral Small 24B Instruct 2501?

Yes, AMD Instinct MI350X 288GB can run Mistral Small 24B Instruct 2501 with a C grade (Runs well). Expected decode speed: 336.0 tok/s.

How much VRAM does Mistral Small 24B Instruct 2501 need?

Mistral Small 24B Instruct 2501 (24B parameters) requires approximately 47.2 GB of memory with Q4_K_M quantization.

What is the best quantization for Mistral Small 24B Instruct 2501?

The recommended quantization for Mistral Small 24B Instruct 2501 is Q4_K_M, which balances quality and memory efficiency.

What speed will Mistral Small 24B Instruct 2501 run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Mistral Small 24B Instruct 2501 achieves approximately 336.0 tokens per second decode speed with a time-to-first-token of 576ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Mistral Small 24B Instruct 2501 for coding?

For coding workloads, Mistral Small 24B Instruct 2501 on AMD Instinct MI350X 288GB receives a C grade with 336.0 tok/s and 1.4M context.

What context window can Mistral Small 24B Instruct 2501 use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Mistral Small 24B Instruct 2501 can safely use up to 1.4M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for Mistral Small 24B Instruct 2501

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-maziyarpanahi--mistral-small-24b-instruct-2501-gguf-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: