Mistral Small 3

Mistral23.6B paramsApache 2.032K contextReleased 2025-01-30

A 23.6B dense model built explicitly for low latency — Mistral aimed this one at "fast enough to feel instant" rather than maximum benchmark score, and it shows in how little VRAM it needs.

Last verified 2026-07 · Page created; Q4_K_M/Q5_K_M/Q8_0/FP16 sizes verified against bartowski/Mistral-Small-24B-Instruct-2501-GGUF.

What it is good at

Mistral Small 3 (internally the 24B-class "2501" checkpoint) was released in January 2025 explicitly optimized for latency — Mistral's stated goal was a model that responds fast enough for real-time use without a round trip to a datacenter, not a benchmark-maximizing flagship. Apache 2.0 licensed, no usage restrictions.

It is a solid fit for local agents and function-calling workflows where response speed compounds across many small calls, more than for long, deliberate reasoning sessions.

The hardware it wants

Q4_K_M is 14.33 GB, fitting a 16 GB GPU with a little headroom, and running very comfortably on any 24 GB card. Q5_K_M (16.76 GB) is the practical ceiling for a 16 GB card; Q8_0 (25.05 GB) needs 32 GB or two pooled 24 GB GPUs. This is one of the more forgiving models in this registry for mid-range hardware — a single 16 GB card (RTX 4060 Ti 16GB, RTX 5060 Ti 16GB) covers it at Q4.

VRAM by quantization

QuantFile sizeVRAM @ 8K ctxVRAM @ 32K ctx8 GB16 GB24 GB32 GB48 GB
FP1647.1 GB57.6 GB67.8 GBDoesn't fitDoesn't fitDoesn't fitDoesn't fitDoesn't fit
Q8_025.1 GB32.2 GB42.4 GBDoesn't fitDoesn't fitDoesn't fitTight — reduced contextFits comfortably
Q5_K_M16.8 GB22.7 GB32.8 GBDoesn't fitDoesn't fitFits comfortablyFits comfortablyFits comfortably
Q4_K_M14.3 GB19.9 GB30.1 GBDoesn't fitDoesn't fitFits comfortablyFits comfortablyFits comfortably

Fit verdicts use the 8K context preset. Estimated from published weight sizes plus standard KV-cache math — see methodology.

Runs on

RX 7900 XT (20 GB)
best fit Q4_K_MFits comfortably
RTX 4090 (24 GB)
best fit Q5_K_MFits comfortably
RX 7900 XTX (24 GB)
best fit Q5_K_MFits comfortably
RTX 5090 (32 GB)
best fit Q8_0Tight — reduced context
RTX 6000 Ada (48 GB)
best fit Q8_0Fits comfortably

Unified-memory machines — Apple Silicon Mac Studio/MacBook Pro (Max/Ultra chips) and AMD Strix Halo mini-PCs — share system RAM and GPU memory in one pool, so a 64–128 GB configuration can hold models that would otherwise need multiple discrete GPUs. Throughput is bandwidth-bound like any GPU; it isn’t modeled in the table above yet.

Recommended builds

Three ways to size a machine for Mistral Small 3, from the smallest GPU that fits to the no-compromise option with headroom for the next model up.

BudgetSmallest GPU that fits at Q4 — runs it, no headroom for bigger contexts.
BalancedOne tier up — comfortable context length, room to run alongside other apps.
No-compromiseFits at Q8 or FP16, or leaves room to step up to the next model class.

Tokens/sec expectations

GPUBandwidthEst. tok/s (Q4_K_M)
RTX 50901792 GB/s~87.5
RTX 40901008 GB/s~49.2
RTX 6000 Ada960 GB/s~46.9
RX 7900 XTX960 GB/s~46.9
RTX 5080960 GB/s~46.9
RTX 5070 Ti896 GB/s~43.8

Estimated from memory bandwidth ÷ active weight size — a ceiling, not a measured figure. Real throughput depends on the inference engine, batch size, and context length.

Build it, or rent the compute?

Owning the hardware is a one-time cost that keeps paying off the more you actually use it — every run after the first is free, the data never leaves your machine, and the GPU still does everything else a PC does (gaming, editing, the rest of your workload) between AI sessions. Renting cloud GPU time trades that upfront cost for pay-as-you-go pricing with no idle hardware to maintain, which wins for occasional, bursty, or much-larger-than-consumer-VRAM jobs. For a model that fits comfortably in the VRAM tiers above and gets used regularly, owning the GPU tends to be the cheaper path over time — for anything larger than a single card can hold, renting is often the more practical starting point.

Frequently asked questions

Can I run Mistral Small 3 on a 16 GB GPU?

Yes — Q4_K_M is 14.33 GB, fitting a 16 GB card with room for context, and Q5_K_M at 16.76 GB is close to the ceiling on the same card.

How is this different from Mistral Small 3.1?

This page covers the original January 2025 "2501" release. 3.1 added vision input and an expanded context window on top of the same size class — if you need image understanding, look at the 3.1 checkpoint specifically; VRAM needs are similar.

Is this a good model for local agent/tool-calling workflows?

Yes — it was tuned for low latency and supports function calling, which is exactly what benefits from fast responses when a workflow makes many small model calls in sequence.

Related models:Gemma 3 27B