TokenAssemble

Mistral AI · open-weights model

Mistral-Small-24B-Instruct-2501

Mistral-Small-24B-Instruct-2501 is a 23.6B-parameter model by Mistral AI. Its smallest quant (Q4_K_M) needs at least 16.2GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 21 of the 50 machines we track.

Parameters
23.6B
Layers
40
Max context
32K
Attention
GQA
License
apache-2.0

Config from mistralai/Mistral-Small-24B-Instruct-2501

Quants and what they need

Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.

QuantFile sizeNeeds ≥
Q8_025.1 GB26.9 GB
Q6_K19.4 GB21.2 GB
Q5_K_M16.8 GB18.6 GB
Q4_K_M14.3 GB16.2 GB

What runs Mistral-Small-24B-Instruct-2501

Every machine we track, graded at its best clean-fit quant.

HardwareBest-quant verdict · llama.cpp · 8K context
Intel Arc A770 16 GBTight · C · Q4_K_Musable · offloadbeta
Intel Arc B580Tight · C · Q4_K_Musable · offloadbeta
AMD Radeon PRO W7900Fits · A+ · Q8_0interactivebeta
NVIDIA GeForce RTX 3060 12 GBTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 3070Tight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 3070 TiTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 3080 10 GBTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 3080 12 GBTight · C · Q4_K_Minteractive · offloadbeta
NVIDIA GeForce RTX 3080 TiTight · C · Q4_K_Minteractive · offloadbeta
NVIDIA GeForce RTX 3090Fits · B · Q5_K_Minteractive
NVIDIA GeForce RTX 3090 TiFits · B · Q5_K_Minteractive
NVIDIA GeForce RTX 4060Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4060 Ti 16 GBTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4060 Ti 8 GBTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4070Tight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4070 SUPERTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4070 TiTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4070 Ti SUPERTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4080Tight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4080 SUPERTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4090Fits · B · Q5_K_Minteractive
NVIDIA RTX 5000 Ada GenerationFits · B · Q8_0usable
NVIDIA GeForce RTX 5060 Ti 16 GBTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 5070Tight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 5070 TiTight · C · Q4_K_Minteractive · offloadbeta
NVIDIA GeForce RTX 5080Tight · C · Q4_K_Minteractive · offloadbeta
NVIDIA GeForce RTX 5090Fits · B · Q8_0interactive
NVIDIA RTX 6000 Ada GenerationFits · A+ · Q8_0interactive
NVIDIA RTX A6000Fits · A+ · Q8_0interactive
AMD Radeon RX 6800Tight · C · Q4_K_Musable · offloadbeta
AMD Radeon RX 6900 XTTight · C · Q4_K_Musable · offloadbeta
AMD Radeon RX 7800 XTTight · C · Q4_K_Musable · offloadbeta
AMD Radeon RX 7900 XTFits · B · Q4_K_Minteractivebeta
AMD Radeon RX 7900 XTXFits · B · Q5_K_Minteractivebeta
AMD Radeon RX 9070Tight · C · Q4_K_Musable · offloadbeta
AMD Radeon RX 9070 XTTight · C · Q4_K_Musable · offloadbeta
ASUS Ascent GX10Fits · A+ · Q8_0painfulbeta
Beelink GTR9 Pro Ryzen AI Max+ 395 128GBFits · A+ · Q8_0painfulbeta
NVIDIA DGX SparkFits · A+ · Q8_0painfulbeta
Framework Desktop Ryzen AI Max+ 395 128GBFits · A+ · Q8_0painfulbeta
Framework Desktop Ryzen AI Max+ 395 64GBFits · A+ · Q8_0painfulbeta
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBFits · A+ · Q8_0painfulbeta
HP Z2 Mini G1a Ryzen AI Max+ PRO 395 128GBFits · A+ · Q8_0painfulbeta
Mac mini M4 16GBWon't fit
Mac mini M4 24GBTight · C · Q4_K_Mpainful
Mac mini M4 Pro 24GBTight · C · Q4_K_Musable
Mac mini M4 Pro 48GBFits · B · Q8_0painful
Mac Studio M3 Ultra 96GBFits · A+ · Q8_0usable
Mac Studio M4 Max 36GBFits · B · Q6_Kusable
Mac Studio M4 Max 64GBFits · A+ · Q8_0usable

Verdicts computed from published specs and measured GGUF sizes — how the math works.