Skip to content
Local AI Wizard
Your machine
Theme

Mistral Small 3.2 24B

Mistral · mistralai/Mistral-Small-3.2-24B-Instruct-2506

Q4 file 14.3 GB (Q4_K_M) · runs well from 24 GB · Weights license: Apache 2.0

LMArena · text1,356 ± 5Rank 212 · release 2026-10-22 · its own scale
Memory needed~19 GBQ4 weights + working room, before the machine's reserve
Parameters24 BHub safetensors count
Context131,072 tokensPublished for this model

Quality

LMArena · text · rating
1,356 ± 5Confidence interval 1,351–1,361 · 17,454 votes · rank 212 of the release · Arena lists Mistral Small 3.2 (2506), earlier under Mistral's API name mistral-small-2506; Mistral's own model card for Mistral Small 3.2 (version 25.06) gives that API name and these open weightsLMArena 2026-10-22 · CC BY 4.0

No result in LiveBench 2026-06-25 Not in LiveBench 2026-06-25

Reported by the publisher

17 results · Mistral's model card · read 2026-10-25
Wildbench v2
65.33%Instruction Following / Chat / Tone
Arena Hard v2
43.1%Instruction Following / Chat / Tone
IF (Internal; accuracy)
84.78%Instruction Following / Chat / Tone
Infinite Generations (Internal; Lower is better)
1.29%Infinite Generations
MMLU
80.50%STEM
MMLU Pro (5-shot CoT)
69.06%STEM · 5-shot
MATH
69.42%STEM
GPQA Main (5-shot CoT)
44.22%STEM · 5-shot
Every reported result17
GPQA Diamond (5-shot CoT)
46.13%STEM · 5-shot
MBPP Plus - Pass@5
78.33%STEM
HumanEval Plus - Pass@5
92.90%STEM
SimpleQA (TotalAcc)
12.10%STEM
MMMU
62.50%Vision
Mathvista
67.09%Vision
ChartQA
87.4%Vision
DocVQA
94.86%Vision
AI2D
92.91%Vision

Values as printed on the card, with the publisher's own settings (card section: Benchmark Results › Text › Instruction Following / Chat / Tone; Benchmark Results › Text › Infinite Generations); column “Small 3.2 24B Instruct”. Not comparable across publishers and not used in any ranking. Model card

Run it

Run it

File Q4_K_M · 14.3 GB · unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF · What is Q4?

Measured 19–101 tok/s · Q4_K_M · 6 machines · Local LLM Advisor · all rows

ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M
  1. Install Ollama
  2. Run the command above
  3. Ask: Explain what a context window is, in two sentences.

Runs on

Fast memory holds it 48

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 48

Within memory, outside the fast part 45

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 45

One memory tier short 9

The same machines with the next memory size up would hold it in fast memory.

Show all 9

Mistral Small 3.2 24B is a text model from Mistral with 24B parameters. It was released on June 20, 2025 and reads up to 131,072 tokens of context. Its Q4 weights plus working room come to about 19 GB before the machine's reserve; the smallest reference machines whose fast memory holds that are Mac mini M4 · 32 GB unified (~27 GB with its reserve) and RTX 4090 · 24 GB VRAM (~21 GB with its reserve). We collected 29 downloadable GGUF and MLX files from 3 publisher sources; the most downloaded GGUF source is unsloth's. It has no result in LiveBench 2026-06-25. Its LMArena text rating is 1,356 ± 5 (release 2026-10-22), a separate human-preference scale.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.

On the reference machines

Mistral Small 3.2 24B on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~21 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 16 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~23 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 24 GB unifiedLarger than its memoryIQ4_XSGGUF · 12.8 GB · needs ~23 GB8,192 tokens~25 GBLarger than its memoryIQ4_XSGGUF · 12.8 GB · needs ~23 GB8,192 tokens
Mac mini M4 · 32 GB unifiedFast memory holds itQ5_K_MGGUF · 16.8 GB · needs ~30 GB16,384 tokens~27 GBFast memory holds itQ5_K_MGGUF · 16.8 GB · needs ~30 GB16,384 tokens
Mac mini M5 Pro · 64 GB unifiedFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB65,536 tokens~27 GBFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB65,536 tokens
Mac Studio M5 Max · 128 GB unifiedFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB131,072 tokens~27 GBFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB131,072 tokens
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB131,072 tokens~27 GBFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB131,072 tokens
RTX 4060 · 8 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~21 GBIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 3060 · 12 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~21 GBIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5080 · 16 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~21 GBIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 4090 · 24 GB VRAMFast memory holds itQ5_K_MGGUF · 16.8 GB · needs ~24 GB8,192 tokens~21 GBFast memory holds itQ5_K_MGGUF · 16.8 GB · needs ~24 GB8,192 tokens
RTX 5090 · 32 GB VRAMFast memory holds itQ6_KGGUF · 19.3 GB · needs ~27 GB32,768 tokens~21 GBFast memory holds itQ6_KGGUF · 19.3 GB · needs ~27 GB32,768 tokens
DGX H100 · 8 × 80 GBFast memory holds itQ8_0GGUF · 25.1 GB · needs ~48 GB131,072 tokens~35 GBFast memory holds itQ8_0GGUF · 25.1 GB · needs ~48 GB131,072 tokens

The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.

Plan another quantization or context

Consider it for

Compare Mistral Small 3.2 24B using its publisher card. No overall score appears in the LiveBench 2026-06-25 snapshot.

Check first

The Q4 weights plus working room come to about 19 GB from 24.01B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Versions to download

Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth, at Q4_K_M. On a Mac it opens on the most downloaded MLX source. Sizes are the Hub's published bytes. What is Q4?

unsloth

unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF · Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf · 14.3 GB

Run this file

ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M
llama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M
lms get https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)

Fine-tunes, adapters and other versions66 fine-tunes
Quantized versions
72
Fine-tunes
66
Adapters · merges
19 · 4

Browse them on the Hugging Face model tree · read 2026-10-23

Uncensored and abliterated versions4

Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.

4 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).

Measured speed

Tokens per second by machine

Output tok/s · 6 machines · fastest 5 of 7 · every row in the table · What is a token?

RTX 5090 · Q4_K_M, 101.14 ± 0.24 · Q4_K_M101.1
RTX 5090 · Q8_0, 63.85 ± 0.10 · Q8_063.9
RTX 4090 24 GB · Q4_K_M, 61.56 ± 0.07 · Q4_K_M61.6
RTX 5080 16 GB · Q4_K_M, 58.64 ± 0.05 · Q4_K_M58.6
RTX 3090 24 GB · Q4_K_M, 53.15 ± 0.01 · Q4_K_M53.2
Measured speed
RTX 5090NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host)101.14 ± 0.24Q4_K_M0 / 128 · Single llama-bench processllama.cpp CUDAllama.cpp commit 3e4dfa8f3 (b11658)Flash Attention enabledunsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf
RTX 5090NVIDIA GeForce RTX 5090 · 32 GB (the card's only memory size; rented host)63.85 ± 0.10Q8_00 / 128 · Single llama-bench processllama.cpp CUDAllama.cpp commit 3e4dfa8f3 (b11658)Flash Attention enabledunsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/Mistral-Small-3.2-24B-Instruct-2506-Q8_0.gguf
RTX 4090 24 GBNVIDIA GeForce RTX 4090 · 24 GB (the card's only memory size; rented host)61.56 ± 0.07Q4_K_M0 / 128 · Single llama-bench processllama.cpp CUDAllama.cpp commit 3e4dfa8f3 (b11658)Flash Attention enabledunsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf
RTX 5080 16 GBNVIDIA GeForce RTX 5080 · 16 GB (the card's only memory size; rented host)58.64 ± 0.05Q4_K_M0 / 128 · Single llama-bench processllama.cpp CUDAllama.cpp commit 3e4dfa8f3 (b11658)Flash Attention enabledunsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf
RTX 3090 24 GBNVIDIA GeForce RTX 3090 · 24 GB (the card's only memory size; rented host)53.15 ± 0.01Q4_K_M0 / 128 · Single llama-bench processllama.cpp CUDAllama.cpp commit 3e4dfa8f3 (b11658)Flash Attention enabledunsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf
RTX 5070 Ti 16 GBNVIDIA GeForce RTX 5070 Ti · 16 GB (the card's only memory size; rented host)52.85 ± 0.07Q4_K_M0 / 128 · Single llama-bench processllama.cpp CUDAllama.cpp commit 3e4dfa8f3 (b11658)Flash Attention enabledunsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf
RTX 4060 Ti 16GBNVIDIA GeForce RTX 4060 Ti · 16 GB (the dataset id names 16 GB; rented host)19.08 ± 0.00Q4_K_M0 / 128 · Single llama-bench processllama.cpp CUDAllama.cpp commit 3e4dfa8f3 (b11658)Flash Attention enabledunsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf

Source: Data: Local LLM Advisor (localllmadvisor.com) · CC BY 4.0 (checked 2026-10-25) · llama.cpp CUDA · llama.cpp commit 3e4dfa8f3 (b11658) · not estimated

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Evidence level: Generic estimate only; no execution reproduced by this site.

Publisher sampling defaults
temperature 0.15generation_config.json · read 2026-10-23source
Chat template markers
— Chat template not read for this checkpoint
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task and modality
language and reasoning · text + image
Count and basis
24B · Hub safetensors countmistralai/Mistral-Small-3.2-24B-Instruct-2506 Hugging Face Hub metadata: safetensors parameter count · read 2026-10-17source
Context
131,072 tokens published for this modelmistralai/Mistral-Small-3.2-24B-Instruct-2506 config.json (Hugging Face) · read 2026-10-17source
Architecture
Densemistralai/Mistral-Small-3.2-24B-Instruct-2506 config.json (Hugging Face) · read 2026-10-17source
Released
Mistral platform-docs-public changelog 2025-06-20 (GitHub) · read 2026-10-17source
Runtime and precision
No local execution verified.
Languages
en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa, id, ms, ne, pl, ro, sr, sv, tr, uk, vi, hi, bnModel card metadata · read 2026-10-25source
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Every stored field11 fields
Revision checked
95a6d26c4bfb886c58daf9d3f7332c857cb27b43
Architecture
Mistral3ForConditionalGeneration
Library
vllm
Declared base models
mistralai/Mistral-Small-3.1-24B-Base-2503
Formats
safetensors
Access
Open download
Publisher kind
Official
Repository created
2025-06-19creation is not the model's release
Repository updated
2025-12-22a commit is not a release date
Hub downloads (30 days) · likes
181,449 · 640this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

The 24.0B is the Hugging Face Hub's safetensors count for this repository, not a publisher figure. The 3.2 card states no parameter count and calls this a minor update of Mistral Small 3.1, whose card says 24 billion parameters. The Q4 estimate on this page is a generic planning figure, not a measured requirement.

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-10-17. Benchmark release: 2026-06-25; snapshot collected: 2026-10-18.