Mistral · 9B to 32B

Mistral Small 24B Instruct 2501

23.57 billion parameters across 40 layers. At four-bit precision the weights alone come to 13.25 GB, before any conversation is loaded. Grouped-query attention keeps the cache small, so long contexts cost less here than on models of the same size.

General chatCoding
Parameters23.57B
Layers40
KV heads8 / 32
Native context32k
Vocabulary131k

Memory needed, by quantisation

At an 8k context window. Quality is our rough ranking of how much the compression costs you: anything at or above Q5 is hard to tell apart from the original in normal use.

Quantisation File size KV cache Total VRAM Quality What it costs you
Q8_0 23.32 GB 1.25 GB 25.49 GB 99% Lossless in practice. Use it when the memory is there.
Q6_K 18 GB 1.25 GB 20.16 GB 98% Very close to Q8 for two thirds of the size.
Q5_K_M 15.61 GB 1.25 GB 17.78 GB 96% The quality-first choice when Q6 will not fit.
Q4_K_M 13.25 GB 1.25 GB 15.42 GB 93% The default. Best size-to-quality ratio for local use.
IQ4_XS 11.66 GB 1.25 GB 13.83 GB 91% Importance-matrix 4-bit. Q4_K_S quality, smaller file.
Q3_K_M 10.73 GB 1.25 GB 12.89 GB 86% Degradation starts to show. A way to fit one size up.
IQ3_XXS 8.4 GB 1.25 GB 10.56 GB 79% Aggressive. Only worth it on very large models.

What a longer conversation costs

Same model at Q4_K_M, only the context window changes. The cache grows in a straight line with every token in the window.

ContextKV cacheTotal VRAMFits in 8 GBFits in 12 GBFits in 24 GB
4k 0.63 GB 14.64 GB no no yes
8k 1.25 GB 15.42 GB no no yes
16k 2.5 GB 16.98 GB no no yes
32k 5 GB 20.1 GB no no yes

The "fits" columns allow for the roughly 0.8 GB Windows keeps for the desktop.

Which hardware runs Mistral Small 24B Instruct 2501

75 of 118 consumer devices run it at a quantisation worth using, at an 8k context window. Another 25 can load it only by compressing the weights far enough to damage the model, marked with a warning below.

DeviceMemoryVerdictQuantisationUsedSpeed
GeForce RTX 5090
NVIDIA
32 GB Runs great Q8_0 25.49 GB 59.8 t/s
RTX PRO 6000 Blackwell
NVIDIA
96 GB Runs great Q8_0 25.49 GB 59.8 t/s
RTX 6000 Ada Generation
NVIDIA
48 GB Runs great Q8_0 25.49 GB 32 t/s
Apple M3 Ultra 96GB
Apple
96 GB Runs great Q8_0 25.19 GB 26 t/s
Apple M3 Ultra 256GB
Apple
256 GB Runs great Q8_0 25.19 GB 26 t/s
Apple M3 Ultra 512GB
Apple
512 GB Runs great Q8_0 25.19 GB 26 t/s
RTX A6000
NVIDIA
48 GB Runs great Q8_0 25.49 GB 25.6 t/s
Apple M1 Ultra 64GB
Apple
64 GB Runs great Q8_0 25.19 GB 25.4 t/s
Apple M1 Ultra 128GB
Apple
128 GB Runs great Q8_0 25.19 GB 25.4 t/s
Apple M2 Ultra 64GB
Apple
64 GB Runs great Q8_0 25.19 GB 25.4 t/s
Apple M2 Ultra 128GB
Apple
128 GB Runs great Q8_0 25.19 GB 25.4 t/s
Apple M2 Ultra 192GB
Apple
192 GB Runs great Q8_0 25.19 GB 25.4 t/s
Radeon PRO W7900
AMD
48 GB Runs great Q8_0 25.49 GB 25.3 t/s
GeForce RTX 4090
NVIDIA
24 GB Runs great Q6_K 20.16 GB 42.9 t/s
GeForce RTX 3090 Ti
NVIDIA
24 GB Runs great Q6_K 20.16 GB 42.9 t/s
GeForce RTX 3090
NVIDIA
24 GB Runs great Q6_K 20.16 GB 39.9 t/s
GeForce RTX 5090 Laptop
NVIDIA
24 GB Runs great Q6_K 20.16 GB 38.2 t/s
Radeon RX 7900 XTX
AMD
24 GB Runs great Q6_K 20.16 GB 35.9 t/s
RTX A5000
NVIDIA
24 GB Runs great Q6_K 20.16 GB 32.7 t/s
Apple M4 Max 36GB
Apple
36 GB Just fits Q8_0 25.19 GB 17.3 t/s
Apple M4 Max 48GB
Apple
48 GB Runs well Q8_0 25.19 GB 17.3 t/s
Apple M4 Max 64GB
Apple
64 GB Runs well Q8_0 25.19 GB 17.3 t/s
Apple M4 Max 128GB
Apple
128 GB Runs well Q8_0 25.19 GB 17.3 t/s
Radeon RX 7900 XT
AMD
20 GB Runs great Q5_K_M 17.78 GB 34.2 t/s
Apple M1 Max 32GB
Apple
32 GB Runs well Q6_K 19.86 GB 16.2 t/s
Apple M2 Max 32GB
Apple
32 GB Runs well Q6_K 19.86 GB 16.2 t/s
GeForce RTX 5080
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 61 t/s
GeForce RTX 5070 Ti
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 56.9 t/s
GeForce RTX 5080 Laptop
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 48.8 t/s
GeForce RTX 4080 SUPER
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 46.7 t/s
GeForce RTX 4080
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 45.5 t/s
GeForce RTX 4070 Ti SUPER
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 42.7 t/s
GeForce RTX 4090 Laptop
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 36.6 t/s
Radeon RX 9070 XT
AMD
16 GB Runs great IQ4_XS 13.83 GB 36 t/s
Radeon RX 9070
AMD
16 GB Runs great IQ4_XS 13.83 GB 36 t/s
Radeon RX 7800 XT
AMD
16 GB Runs great IQ4_XS 13.83 GB 34.8 t/s
Radeon RX 7900 GRE
AMD
16 GB Runs great IQ4_XS 13.83 GB 32.1 t/s
Radeon RX 6900 XT
AMD
16 GB Runs great IQ4_XS 13.83 GB 28.6 t/s
Radeon RX 6800
AMD
16 GB Runs great IQ4_XS 13.83 GB 28.6 t/s
GeForce RTX 5060 Ti 16GB
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 28.5 t/s
RTX A4000
NVIDIA
16 GB Runs great IQ4_XS 13.83 GB 28.5 t/s
Arc A770 16GB
Intel
16 GB Runs great IQ4_XS 13.83 GB 28.2 t/s
Apple M1 Max 64GB
Apple
64 GB Runs well Q8_0 25.19 GB 12.7 t/s
Apple M2 Max 64GB
Apple
64 GB Runs well Q8_0 25.19 GB 12.7 t/s
Apple M2 Max 96GB
Apple
96 GB Runs well Q8_0 25.19 GB 12.7 t/s
Apple M3 Max 36GB
Apple
36 GB Just fits Q8_0 25.19 GB 12.7 t/s
Apple M3 Max 48GB
Apple
48 GB Runs well Q8_0 25.19 GB 12.7 t/s
Apple M3 Max 64GB
Apple
64 GB Runs well Q8_0 25.19 GB 12.7 t/s
Apple M3 Max 96GB
Apple
96 GB Runs well Q8_0 25.19 GB 12.7 t/s
Apple M3 Max 128GB
Apple
128 GB Runs well Q8_0 25.19 GB 12.7 t/s
GeForce RTX 4060 Ti 16GB
NVIDIA
16 GB Runs well IQ4_XS 13.83 GB 18.3 t/s
NVIDIA DGX Spark 128GB
NVIDIA
128 GB Runs well Q6_K 20.16 GB 11.6 t/s
Apple M4 Pro 24GB
Apple
24 GB Runs well Q4_K_M 15.12 GB 14.7 t/s
Radeon RX 7600 XT
AMD
16 GB Runs well IQ4_XS 13.83 GB 16.1 t/s
Apple M4 Pro 48GB
Apple
48 GB Runs well Q6_K 19.86 GB 11.1 t/s
Apple M4 Pro 64GB
Apple
64 GB Runs well Q6_K 19.86 GB 11.1 t/s
Jetson AGX Orin 32GB
NVIDIA
32 GB Fits, but slow Q5_K_M 17.78 GB 10 t/s
Jetson AGX Orin 64GB
NVIDIA
64 GB Fits, but slow Q5_K_M 17.78 GB 10 t/s
Ryzen AI Max+ 395 32GB
AMD
32 GB Runs well Q4_K_M 15.42 GB 11.5 t/s
Ryzen AI Max+ 395 64GB
AMD
64 GB Runs well Q4_K_M 15.42 GB 11.5 t/s

What to buy to run Mistral Small 24B Instruct 2501

The cheapest hardware that runs it at a quantisation worth using and a speed you would not resent, at an 8k context window.

DevicePriceMemoryRuns it atSpeed
Arc A770 16GB
Intel
$280 used 16 GB IQ4_XS 28.2 t/s Check price
Radeon RX 6800
AMD
$330 used 16 GB IQ4_XS 28.6 t/s Check price
Radeon RX 7800 XT
AMD
$480 16 GB IQ4_XS 34.8 t/s Check price
Radeon RX 9070
AMD
$560 16 GB IQ4_XS 36 t/s Check price
Radeon RX 7900 XT
AMD
$650 20 GB Q5_K_M 34.2 t/s Check price
GeForce RTX 3090
NVIDIA
$700 used 24 GB Q6_K 39.9 t/s Check price
GeForce RTX 4070 Ti SUPER
NVIDIA
$750 16 GB IQ4_XS 42.7 t/s Check price
GeForce RTX 5070 Ti
NVIDIA
$780 16 GB IQ4_XS 56.9 t/s Check price

Indicative prices reviewed 2026-09-01; used prices are marketplace typical. Options that cost more than a cheaper one with no more memory and no more speed are hidden. Price links are Amazon affiliate links. Change the standard, the context window or the budget in the buying tool.

Where it sits in the catalogue

Source: mistralai/Mistral-Small-24B-Instruct-2501 on Hugging Face. Downloaded 45k times in the last month. Published 2025-01-28. Architecture figures are read from the repository's own configuration file, so they move when the model does.