Mistral AIMistralMistral3ForConditionalGeneration

Mistral Small 3.1 24B Instruct 2503 — Hardware Requirements & GPU Compatibility

Chat

Mistral Small 3.1 24B Instruct 2503 is a 24-billion-parameter model from Mistral AI, the French AI lab, built on the earlier text-only Mistral Small 3 with added support for image input alongside text. It can reason about images in the same conversation as written prompts, useful for document understanding and multimodal chat. At 24 billion parameters, it needs quantization and a single high-end 24GB-class consumer or workstation GPU for local inference rather than budget hardware. The model supports a 128K token context window for long documents or extended conversations. It is released under the Apache 2.0 license, allowing unrestricted commercial and research use. Published in March 2025, it added vision understanding and a longer context window to the earlier text-only Mistral Small while keeping the same 24B parameter budget.

24.0B params · dense131K contextApache 2.0Mar 2025169.9K downloads1.4K likes23.2K quant downloads

Your hardware

Verdicts below are for the reference RTX 4090. Set yours to personalise the page.

Detection reads your browser's GPU name with no data sent anywhere.

Runs well on a 24 GB GPU

Runs from 12 GB (IQ2_M · 16K)Best on 24 GB (Q4_K_M · ~43 tok/s · 32K)Macs from 16 GB (IQ2_M · ~16 tok/s)

Score 79#92 of 106 open#27 of 36 that fit 24 GBApache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

llmrun Composite Score →

79.0

90% range 73.0–85.0
#92 of 106 open models
#27 of 36 that fit 24 GB

Benchmarks · tier chart ↓

Among 106 open modelsHow the Composite Score is built

CodingNot enough data yet
AgentsNot enough data yet
MathNot enough data yet
Science81.490% range 73–90
ReasoningNot enough data yet

Run Mistral Small 3.1 24B Instruct 2503

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.

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 24 GB GPU

The easiest way to try this model
Running in a few minutes, easy setup
Chat right here or connect any app

$5+ bonus for new users

Run Mistral Small 3.1 24B Instruct 2503

18.1 GB VRAM at 16K context · fits the RTX 4090 (5.9 GB free)

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run mistral-small3.1:24b
Official Ollama library build. For the exact Q4_K_M file from bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF: ollama run hf.co/bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=16384 ollama serve.
$/set parameter num_ctx 16384
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 16384. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M -c 16384 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Option A: Docker Model Runner
Docker Desktop: Settings > AI > Enable Docker Model Runner. Docker Engine on Linux: install the docker-model-plugin package.
$docker model run hf.co/bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M
Model Runner docs ↗
The quant tag after the repo is how Hugging Face cards write it; if your Docker version rejects it, drop the tag and pick the quant by repo.
Option B: llama.cpp server image (NVIDIA)
Needs the NVIDIA Container Toolkit. Models are cached in the llama-cache volume. Open http://localhost:8080.
$docker run --gpus all -p 8080:8080 -v llama-cache:/root/.cache ghcr.io/ggml-org/llama.cpp:server-cuda -hf bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M -c 16384 -ngl 99 --host 0.0.0.0 --port 8080
Image tags (cuda13, vulkan, rocm) ↗
Cache path inside the image is not in the docs; remove the -v flag if the volume complains.

Linux only.

Install vLLM
Linux only; on Windows run it inside WSL2. NVIDIA GPU shown; AMD ROCm, Intel and CPU builds have their own install pages.
$uv venv --python 3.12 --seed
$source .venv/bin/activate
$uv pip install vllm --torch-backend=auto
vLLM installation ↗
Serve the model
OpenAI-compatible API at http://localhost:8000/v1.
$vllm serve mistralai/Mistral-Small-3.1-24B-Instruct-2503 --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~53 GB of GPU memory.

macOS only.

MLX supports only macOS, so follow these steps for that setup.

Install mlx-lm
$pip install mlx-lm
Chat in the terminal
$mlx_lm.chat --model luiscalisto/Mistral-Small-3.1-24B-Instruct-2503-MLX-4bit
Downloads the model on first run. The MLX repo has its own quantisation; it may not match the quant selected above.
Or start a local server
Listens on http://localhost:8080.
$mlx_lm.server --model luiscalisto/Mistral-Small-3.1-24B-Instruct-2503-MLX-4bit

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
RTX 3090 (24 GB)CheapestCheapest5 GB free	~40 tok/s	$1.17	Deploy on Vast.aifrom $0.17/hr (opens in new tab)	24 GB · 5 GB free · ~40 tok/s · $1.17 / 1M tokens
RTX A5000 (24 GB)5 GB free	~33 tok/s	$1.35	Deploy on RunPodfrom $0.16/hr (opens in new tab)	24 GB · 5 GB free · ~33 tok/s · $1.35 / 1M tokens
TITAN RTX (24 GB)5 GB free	~29 tok/s	$2.07	Deploy on Vast.aifrom $0.22/hr (opens in new tab)	24 GB · 5 GB free · ~29 tok/s · $2.07 / 1M tokens
RTX A5000 (24 GB)5 GB free	~33 tok/s	$1.93	Deploy on Vast.aifrom $0.23/hr (opens in new tab)	24 GB · 5 GB free · ~33 tok/s · $1.93 / 1M tokens
RTX 3090 Ti (24 GB)5 GB free	~43 tok/s	$1.72	Deploy on Vast.aifrom $0.27/hr (opens in new tab)	24 GB · 5 GB free · ~43 tok/s · $1.72 / 1M tokens
RTX PRO 4500 (32 GB)13 GB free	~39 tok/s	$2.45	Deploy on RunPodfrom $0.34/hr (opens in new tab)	32 GB · 13 GB free · ~39 tok/s · $2.45 / 1M tokens
RTX 4090 (24 GB)5 GB free	~43 tok/s	$2.18	Deploy on RunPodfrom $0.34/hr (opens in new tab)	24 GB · 5 GB free · ~43 tok/s · $2.18 / 1M tokens
A40 (48 GB)29 GB free	~30 tok/s	$3.25	Deploy on RunPodfrom $0.35/hr (opens in new tab)	48 GB · 29 GB free · ~30 tok/s · $3.25 / 1M tokens

Compare GPUs →

Your own private copy of Mistral Small 3.1 24B Instruct 2503 · Q4_K_M · OpenAI-compatible API

Open the llama.cpp listing on RunPod
Open on RunPodServerless (opens in new tab)
New to RunPod? Sign up and add credit first.
2
Fill in the form
Press Deploy and fill in:
Model
bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF
Quantization
Q4_K_M
Context Size
16384
After pasting the model press Esc — don’t pick a suggestion. Press Next.
Create the endpoint
Keep the default 24 GB and 48 GB, then Create Endpoint. Right away: Manage → Edit endpoint → Max workers 1 → Save (changing settings later restarts the worker).
The first start downloads the model, usually 5–15 min. After that, replies after a pause come in seconds.
Create an API key
RunPod → Settings → API Keys → Create. Pick “Restricted” with access to this endpoint only.

Use it

Copy the endpoint URL from its page on RunPod (any of its links works) and paste it with the key. Both stay in this browser.

Endpoint URL

API key

Chats and keys stay only in this browser.

https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1

Put your endpoint ID in place of <ENDPOINT_ID>. The API key is the one from step 2.

from openai import OpenAI
client = OpenAI(base_url="https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1", api_key="rpa_...")
r = client.chat.completions.create(
    model="any",
    messages=[{"role": "user", "content": "Hello!"}])
print(r.choices[0].message.content)

Works with any OpenAI client.

https://api.runpod.ai/v2/<ENDPOINT_ID>/openai/v1

Put your endpoint ID in place of <ENDPOINT_ID>. The API key is the one from step 2.

Free on Windows, macOS, Linux, iOS, Android and the web.

Open the web app ↗ (opens in a new tab)Download ↗ (opens in a new tab)

1. Settings → Model Provider → Add → Add Custom Provider
2. API Mode OpenAI API Compatible; paste the API key and the base URL as API Host
3. Model → Fetch, pick the model
4. New chat → pick the provider → start chatting

Free and open source for Windows, macOS and Linux.

Download Jan ↗ (opens in a new tab)

1.Settings → next to Model Providers press +
2.API format OpenAI-compatible; Base URL is the base URL above (with /v1); API key is your key; Create
3.If no model appears, click + in Models and type any
4.New chat → pick the model → start chatting

How Much VRAM Does Mistral Small 3.1 24B Instruct 2503 Need?

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

VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
7.3 GB	13.6 GB	33.7 GB	6.5 GB	2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss	Fits: 64K context · ~90 tok/s
7.9 GB	14.2 GB	34.3 GB	7.2 GB	2-bit · i-quant extra small — Importance-weighted 2-bit, extra small	Fits: 64K context · ~83 tok/s
8.2 GB	14.5 GB	34.6 GB	7.5 GB	2-bit · i-quant small — Importance-weighted 2-bit, small	Fits: 64K context · ~80 tok/s
8.8 GB	15.1 GB	35.2 GB	8.1 GB	2-bit · i-quant medium — Importance-weighted 2-bit, medium	Fits: 64K context · ~74 tok/s
10.0 GB	16.3 GB	36.4 GB	9.3 GB	3-bit · i-quant — Importance-weighted 3-bit	Fits: 64K context · ~65 tok/s
10.3 GB	16.6 GB	36.7 GB	8.3 GB	2-bit · small K-quant — 2-bit small K-quant	Fits: 64K context · ~64 tok/s
10.6 GB	16.9 GB	37 GB	9.9 GB	3-bit · i-quant extra small — Importance-weighted 3-bit, extra small	Fits: 64K context · ~62 tok/s
10.9 GB	17.2 GB	37.3 GB	8.9 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 64K context · ~60 tok/s
10.9 GB	17.2 GB	37.3 GB	10.4 GB	3-bit · i-quant small — Importance-weighted 3-bit, small	Fits: 64K context · ~60 tok/s
11.2 GB	17.5 GB	37.6 GB	10.4 GB	3-bit small — 3-bit small quantization	Fits: 32K context · ~58 tok/s
11.5 GB	17.8 GB	37.9 GB	10.7 GB	3-bit · i-quant medium — Importance-weighted 3-bit, medium	Fits: 32K context · ~57 tok/s
12.4 GB	18.7 GB	38.8 GB	11.5 GB	3-bit medium — 3-bit medium quantization	Fits: 32K context · ~53 tok/s
12.7 GB	19 GB	39.2 GB	13.5 GB	4-bit · legacy — 4-bit legacy quantization	Fits: 32K context · ~52 tok/s
13.0 GB	19.3 GB	39.5 GB	12.4 GB	3-bit large — 3-bit large quantization	Fits: 32K context · ~50 tok/s
13.6 GB	19.9 GB	40.1 GB	12.8 GB	4-bit · i-quant compact — Importance-weighted 4-bit, compact	Fits: 32K context · ~48 tok/s
14.2 GB	20.5 GB	40.7 GB	13.5 GB	4-bit small — 4-bit small quantization	Fits: 32K context · ~46 tok/s
14.2 GB	20.5 GB	40.7 GB	14.9 GB	4-bit · legacy+ — 4-bit legacy quantization with offset	Fits: 32K context · ~46 tok/s
14.2 GB	20.5 GB	40.7 GB	13.5 GB	4-bit · i-quant non-linear — Importance-weighted 4-bit, non-linear	Fits: 32K context · ~46 tok/s
15.1 GB	21.4 GB	41.6 GB	14.3 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Fits: 32K context · ~43 tok/s
15.4 GB	21.7 GB	41.9 GB	14.8 GB	4-bit large — 4-bit large quantization	Fits: 32K context · ~43 tok/s
15.7 GB	22 GB	42.2 GB	16.3 GB	5-bit · legacy — 5-bit legacy quantization	Fits: 32K context · ~42 tok/s
17.2 GB	23.5 GB	43.7 GB	16.3 GB	5-bit small — 5-bit small quantization	Fits: 32K context · ~38 tok/s
17.2 GB	23.5 GB	43.7 GB	17.7 GB	5-bit · legacy+ — 5-bit legacy quantization with offset	Fits: 32K context · ~38 tok/s
17.8 GB	24.1 GB	44.3 GB	16.8 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Fits: 16K context · ~37 tok/s
18.1 GB	24.4 GB	44.6 GB	17.2 GB	5-bit large — 5-bit large quantization	Fits: 16K context · ~36 tok/s
20.5 GB	26.8 GB	47 GB	19.3 GB	6-bit, very good — 6-bit quantization, very good quality	Fits: 16K context · ~32 tok/s
24.7 GB	31 GB	51.2 GB	25.1 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Does not fit: needs 27.7 GB
48.7 GB	55 GB	75.2 GB	47.2 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 51.7 GB

Selected Q4_K_M

4-bit medium quantization

18.1GBat 16K context

Weights: 14.4 GB
KV cache: 3.4 GB
Overhead: 0.3 GB

Fits RTX 4090 (reference) · 5.9 GB free · ~43 tok/s

≥50 tok/s needs ≥1.16 TB/s · RTX 5090 ~77

Which Hardware Can Run Mistral Small 3.1 24B Instruct 2503?

Q4_K_M · 15.1 GB

Mistral Small 3.1 24B Instruct 2503 (Q4_K_M) requires 15.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 20+ GB is recommended. Using the full 131K context window can add up to 26.4 GB, bringing total usage to 41.5 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 122 devices with unified memory can run Mistral Small 3.1 24B Instruct 2503, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8 GB · RTX 4060Doesn't fit — smallest quant needs 10.3 GB8 GB tier →

12 GB · RTX 3060 12GBIQ2_M · 11.8 GB · ~27 tok/s · 16K11.8~2716K12 GB tier →

16 GB · RTX 5060 Ti 16GBQ4_K_M · 18.1 GB · ~19 tok/s · 4Ktight18.1~194K16 GB tier →

24 GB · RTX 4090referenceQ4_K_M · 18.1 GB · ~43 tok/s · 32K18.1~4332K24 GB tier →

Mac 32 GB · Mac Mini M4Q4_K_M · 18.1 GB · ~6 tok/s · 64K18.1~664KMacs →

Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 18.1 GB · ~25 tok/s · 128K18.1~25128KMacs →

How good is Mistral Small 3.1 24B Instruct 2503?

The llmrun Score merges 5 public benchmark boards into a single figure, where 100 represents the average for open models.

Score vs VRAM in the 24 GB tier

Mistral Small 3.1 24B Instruct 2503
Other models
Best Score for its VRAM
x: VRAM (GB) · y: llmrun Score

#27 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

GPQA Diamond
Epoch AI · Mar 2025Independent
47.5%
#61/100 open
Independent
LMArena Text
LMArena · Oct 2026Arena
1302.6
#108/188 open
Arena
AIME 2024/2025
Epoch AI · Mar 2025Independent
5.8%
#69/88 open
Independent
SciCode
Epoch AI · Mar 2025Lab-reported
27.8%
#62/72 open
Lab-reported
MATH Level 5
Epoch AI · Mar 2025Independent
46.8%
#16/39 open
Independent
CritPt
Epoch AI · Mar 2025Lab-reported
0.0%
#74/84 open
Lab-reported

All 7 Mistral Small 3.1 24B Instruct 2503 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
Qwen3.8 27BAlibaba
122.0
~38 tok/s · 17.9 GB
#2
Qwen3.6 27BAlibaba
111.2
~38 tok/s · 17.9 GB
#3
Qwen3.6 35B A3BAlibaba
106.8
~151 tok/s · 22.0 GB
#4
Gemma 4 31B ITGoogle
106.7
~32 tok/s · 21.7 GB
#5
Gemma 4 26B A4B ITGoogle
105.8
~171 tok/s · 16.5 GB
#6
Qwen3.5 35B A3BAlibaba
105.8
~151 tok/s · 22.0 GB

Full 24 GB ranking →RTX 4090 page →

Alternatives to Mistral Small 3.1 24B Instruct 2503

Mistral family · 35 models →

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

Best alternative at this size
Qwen3.8 27B
Alibaba
- 43 higher Score
- 0.2 GB less VRAM
- 6 tok/s slower
Score 122.0 · 17.9 GB · ~38 tok/s
Compare with Mistral Small 3.1 24B Instruct 2503 Open Qwen3.8 27B
Much faster, similar quality
Qwen3.6 35B A3B
Alibaba
- 27.8 higher Score
- 4 GB more VRAM
- 108 tok/s faster
Score 106.8 · 22 GB · ~151 tok/s
Compare with Mistral Small 3.1 24B Instruct 2503 Open Qwen3.6 35B A3B
Fits in less VRAM
GPT OSS 20B
OpenAI
- 17.4 higher Score
- 4.9 GB less VRAM
- 146 tok/s faster
Score 96.4 · 13.1 GB · ~190 tok/s
Compare with Mistral Small 3.1 24B Instruct 2503 Open GPT OSS 20B
Other vendor
Qwen3.6 27B
Alibaba
- 32.2 higher Score
- 0.2 GB less VRAM
- 6 tok/s slower
Score 111.2 · 17.9 GB · ~38 tok/s
Compare with Mistral Small 3.1 24B Instruct 2503 Open Qwen3.6 27B

Similar models

10tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Gemma 4 31B ITGoogle	106.7	21.7 GB	~32	similar score
Gemma 4 26B A4B ITGoogle	105.8	16.5 GB	~171	similar score
Qwen3.5 35B A3BAlibaba	105.8	22 GB	~151	similar score
Qwen3.5 27BAlibaba	103.8	17.9 GB	~38	similar score
Seed OSS 36B InstructByteDance-Seed	102.5	22.8 GB	~31	similar score
Qwen3 30B A3B Thinking 2507Alibaba	100.7	19.4 GB	~173	similar score
Qwen3 8BAlibaba	93.9	7.6 GB	~119	similar score
Phi 4Microsoft	83.9	12.5 GB	~69	similar score
Qwen2.5 32B InstructAlibaba	80.4	23 GB	~34	similar score
Gemma 3 12B ITGoogle	74.2	10.9 GB	~82	similar score

Fine-tunes & variants(4)community builds of Mistral Small 3.1 24B Instruct 2503

Specifications

Publisher: Mistral AI
Family: Mistral
Parameters: 24.0B
Architecture: Mistral3ForConditionalGeneration
Context Length: 131,072 tokens
Vocabulary Size: 131,072
Release Date: 2025-03-11
License: Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does Mistral Small 3.1 24B Instruct 2503 need?

Mistral Small 3.1 24B Instruct 2503 requires 15.1 GB of VRAM at Q4_K_M, or 48.7 GB at BF16. Full 131K context adds up to 26.4 GB (41.5 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 24.0B × 4.8 bits ÷ 8 = 14.4 GB

KV Cache + Overhead ≈ 0.7 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 ≈ 27.2 GB (at full 131K context)

VRAM usage by quantization

Q4_K_M

15.1 GB

Q4_K_M + full context

41.5 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Mistral Small 3.1 24B Instruct 2503?

Yes, at Q6_K (20.5 GB) or lower. Higher quantizations like Q8_0 (24.7 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Mistral Small 3.1 24B Instruct 2503?

For Mistral Small 3.1 24B Instruct 2503, Q4_K_M (15.1 GB) offers the best balance of quality and VRAM usage. Q4_K_L (15.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 7.3 GB.

VRAM requirement by quantization

IQ2_XXS

7.3 GB~53%

Q2_K

10.9 GB~75%

IQ4_XS

13.6 GB~87%

Q4_K_M ★

15.1 GB~89%

Q5_0

15.7 GB~90%

BF16

48.7 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Mistral Small 3.1 24B Instruct 2503 on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Mistral Small 3.1 24B Instruct 2503, 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 15.1 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).

Can I run Mistral Small 3.1 24B Instruct 2503 locally?

Yes — Mistral Small 3.1 24B Instruct 2503 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Mistral Small 3.1 24B Instruct 2503?

At Q4_K_M, Mistral Small 3.1 24B Instruct 2503 can reach ~317 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~43 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 15.1 × 0.65 = ~344 tok/s

Estimated speed at Q4_K_M (15.1 GB)

NVIDIA B200

~344 tok/s

NVIDIA GeForce RTX 4090

~43 tok/s

NVIDIA B300

~344 tok/s

AMD Instinct MI350X

~317 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 Mistral Small 3.1 24B Instruct 2503?

At Q4_K_M, the download is about 14.41 GB. The full-precision BF16 version is 48.02 GB. The smallest option (IQ2_XXS) is 6.60 GB.

Which GPUs can run Mistral Small 3.1 24B Instruct 2503?

26 consumer GPUs can run Mistral Small 3.1 24B Instruct 2503 at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 7 GPUs have plenty of headroom for comfortable inference.

Which devices can run Mistral Small 3.1 24B Instruct 2503?

122 devices with unified memory can run Mistral Small 3.1 24B Instruct 2503 at Q4_K_M (15.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.

Mistral Small 3.1 24B Instruct 2503 — Hardware Requirements & GPU Compatibility

Runs well on a 24 GB GPU

llmrun Composite Score →

Run Mistral Small 3.1 24B Instruct 2503

Recommended

Ways to runOther ways

Run in cloud

How Much VRAM Does Mistral Small 3.1 24B Instruct 2503 Need?

Selected Q4_K_M

Which Hardware Can Run Mistral Small 3.1 24B Instruct 2503?

How good is Mistral Small 3.1 24B Instruct 2503?

Score vs VRAM in the 24 GB tier

Benchmarks

In the 24 GB class

Alternatives to Mistral Small 3.1 24B Instruct 2503

Qwen3.8 27B

Qwen3.6 35B A3B

GPT OSS 20B

Qwen3.6 27B

Similar models

Specifications

Resources

Frequently Asked Questions