Skip to content
Local AI Wizard
Your machine
Theme

Devstral Small 2 24B

Mistral · mistralai/Devstral-Small-2-24B-Instruct-2512

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

Reported by the publisher3 resultsMistral's model card · read 2026-10-25 · not ranked · see them
Memory needed~18 GBQ4 weights + working room, before the machine's reserve
Parameters24 Bmanufacturer specification
Context262,144 tokensPublished for this model

Quality

No result in LiveBench 2026-06-25, LMArena 2026-10-22 Not in LiveBench 2026-06-25 or LMArena 2026-10-22

Reported by the publisher

3 results · Mistral's model card · read 2026-10-25
SWE Bench Verified
68.0%
SWE Bench Multilingual
55.7%
Terminal Bench 2
22.5%

Values as printed on the card, with the publisher's own settings (card section: Benchmark Results); column “Devstral Small 2”. Not comparable across publishers and not used in any ranking. Model card

Run it

Run it

ollama run hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-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 57

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

Show all 57

Within memory, outside the fast part 47

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 47

One memory tier short 12

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

Show all 12

Devstral Small 2 24B is a text model from Mistral with 24B parameters. It was released on December 9, 2025 and reads up to 262,144 tokens of context. Its Q4 weights plus working room come to about 18 GB before the machine's reserve; the smallest reference machines whose fast memory holds that are Mac mini M4 · 24 GB unified (~24 GB with its reserve) and RTX 4090 · 24 GB VRAM (~20 GB with its reserve). We collected 28 downloadable GGUF and MLX files from 2 publisher sources; the most downloaded GGUF source is unsloth's. It has no result in LiveBench 2026-06-25, so no quality score is shown.

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

Devstral Small 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~20 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~22 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 unifiedFast memory holds itIQ4_XSGGUF · 12.8 GB · needs ~23 GB8,192 tokens~24 GBFast memory holds itIQ4_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~26 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~26 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 GB262,144 tokens~26 GBFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB262,144 tokens
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB262,144 tokens~26 GBFast memory holds itQ8_0GGUF · 25.1 GB · needs ~40 GB262,144 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~20 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~20 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~20 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~20 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~20 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 GB262,144 tokens~34 GBFast memory holds itQ8_0GGUF · 25.1 GB · needs ~48 GB262,144 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 Devstral Small 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 18 GB from 24B 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/Devstral-Small-2-24B-Instruct-2512-GGUF · Devstral-Small-2-24B-Instruct-2512-Q4_K_M.gguf · 14.3 GB

Run this file

ollama run hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_M
llama-server -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_M
lms get https://huggingface.co/unsloth/Devstral-Small-2-24B-Instruct-2512-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 versions4 fine-tunes
Quantized versions
48
Fine-tunes
4
Adapters · merges
50 · 1

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

Uncensored and abliterated versions2

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.

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

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never 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
tool calls · no thinking markersmarkers found in the template, not a test of the feature · read 2026-10-23source
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 · manufacturer specificationmistralai/Devstral-Small-2-24B-Instruct-2512 model card (Hugging Face) · read 2026-10-17source
Context
262,144 tokens published for this modelmistralai/Devstral-Small-2-24B-Instruct-2512 model card (Hugging Face) · read 2026-10-17source
Architecture
Densemistralai/Devstral-Small-2-24B-Instruct-2512 model card (Hugging Face) · read 2026-10-17source
Released
Mistral platform-docs-public changelog 2025-12-09 (GitHub) · read 2026-10-17source
Runtime and precision
No local execution verified.
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Every stored field12 fields
Revision checked
55c5b41e98c2dbd21b0c8afffc540dcfc9eb5128
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
2025-11-28creation is not the model's release
Repository updated
2026-07-15a commit is not a release date
Hub downloads (30 days) · likes
195,608 · 706this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

This instruct checkpoint is shipped in FP8 with a separate vision component. Mistral says it is light enough for a single RTX 4090 or a Mac with 32 GB RAM, without a weight size. The generic Q4 estimate is a different configuration.

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: 2026-09-26.