readygpu

Mistral Small 3.2 24B

24B parameters · 128k context · apache-2.0 · released 2025-06-19

chatcodingvision

What to run it on in the US

Fully in memory at 64k context, priced at retailers today.

All hardware that runs it

Everything we price, best value first. Two cards split the model by layers.

HardwareQuantFitsDecodePricetok/s per 1,000
AMD Radeon AI PRO R9700Q6_Kfits12 tok/s$1,7006.9
NVIDIA GeForce RTX 5090Q6_Kfits37 tok/s$7,2005.1
Mac Studio M4 Max 128GBQ8_0fits10 tok/s––
Mac mini M4 Pro 64GBQ8_0fits5 tok/s––
Framework Desktop Ryzen AI Max+ 395 128GBQ8_0fits4 tok/s––
Mac Studio M3 Ultra 512GBQ8_0fits15 tok/s––
NVIDIA DGX Spark 128GBQ8_0fits5 tok/s––
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBQ8_0fits4 tok/s––
Mac Studio M3 Ultra 256GBQ8_0fits15 tok/s––
Mac mini M4 Pro 48GBQ8_0fits5 tok/s––
Mac Studio M4 Max 64GBQ8_0fits10 tok/s––
Mac Studio M3 Ultra 96GBQ8_0fits15 tok/s––
NVIDIA RTX PRO 6000 BlackwellQ8_0fits31 tok/s––
ASUS Ascent GX10 128GBQ8_0fits5 tok/s––
Framework Desktop Ryzen AI Max+ 395 64GBQ8_0fits4 tok/s––
NVIDIA GeForce RTX 3060 12GBQ4_K_Moffload3 tok/s$3608.9
Intel Arc B580Q4_K_Moffload3 tok/s$3708.6
Intel Arc A770 16GBQ4_K_Moffload4 tok/s$40010.5
NVIDIA GeForce RTX 3080 10GBQ4_K_Moffload3 tok/s$4696.6
AMD Radeon RX 9060 XT 16GBQ4_K_Moffload4 tok/s$5436.8
AMD Radeon RX 7800 XTQ4_K_Moffload4 tok/s$5997.2
Intel Arc Pro B60Q4_K_Moffload8 tok/s$65011.8
AMD Radeon RX 7600 XTQ4_K_Moffload4 tok/s$6955.2
NVIDIA GeForce RTX 4070 SuperQ4_K_Moffload3 tok/s$6994.9
NVIDIA GeForce RTX 4060 Ti 16GBQ4_K_Moffload4 tok/s$7704.9
NVIDIA GeForce RTX 5060 Ti 16GBQ4_K_Moffload4 tok/s$7725.4
NVIDIA GeForce RTX 5070Q4_K_Moffload4 tok/s$7764.5
AMD Radeon RX 7900 XTQ4_K_Moffload7 tok/s$8008.4
AMD Radeon RX 9070 XTQ4_K_Moffload4 tok/s$8155.4
NVIDIA GeForce RTX 4070 Ti SuperQ4_K_Moffload5 tok/s$1,0134.5
NVIDIA GeForce RTX 5070 TiQ4_K_Moffload5 tok/s$1,1444.2
NVIDIA GeForce RTX 4080 SuperQ4_K_Moffload5 tok/s$1,1993.9
AMD Radeon RX 7900 XTXQ4_K_Moffload14 tok/s$1,5339.1
NVIDIA GeForce RTX 3090Q4_K_Moffload16 tok/s$1,6609.8
NVIDIA GeForce RTX 5080Q4_K_Moffload5 tok/s$1,7382.8
NVIDIA GeForce RTX 3090 TiQ4_K_Moffload17 tok/s$2,0608.3
NVIDIA GeForce RTX 4090Q4_K_Moffload17 tok/s$3,2805.2
NVIDIA Tesla P40Q4_K_Moffload8 tok/s––

2 other cards and machines we price cannot hold it at this context.

Memory needed

Weights, KV cache and runtime buffers at each context length (KV cache at fp16).

QuantFile@8k@32k@64k@128k
Q4_K_Mgguf13.3 GB15.3 GB19.2 GB24.4 GB34.8 GB
mlx-4bitmlx12.3 GB14.3 GB18.2 GB23.4 GB33.8 GB
Q5_K_Mgguf15.6 GB17.6 GB21.5 GB26.7 GB37.1 GB
Q6_Kgguf18.0 GB20.0 GB23.9 GB29.1 GB39.5 GB
mlx-8bitmlx23.3 GB25.3 GB29.2 GB34.4 GB44.8 GB
Q8_0gguf23.3 GB25.3 GB29.2 GB34.4 GB44.8 GB

Run it

Copy a command for the runtime you use.

  • Q4_K_M
    • Ollamaollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M
    • LM Studiolms get unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF@q4_k_m
    • llama.cppllama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M
  • mlx-4bit
    • LM Studiolms get mlx-community/Mistral-Small-3.2-24B-Instruct-2506-4bit
    • MLXmlx_lm.server --model mlx-community/Mistral-Small-3.2-24B-Instruct-2506-4bit
  • Q5_K_M
    • Ollamaollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q5_K_M
    • LM Studiolms get unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF@q5_k_m
    • llama.cppllama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q5_K_M
  • Q6_K
    • Ollamaollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q6_K
    • LM Studiolms get unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF@q6_k
    • llama.cppllama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q6_K
  • mlx-8bit
    • LM Studiolms get mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
    • MLXmlx_lm.server --model mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit
  • Q8_0
    • Ollamaollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q8_0
    • LM Studiolms get unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF@q8_0
    • llama.cppllama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q8_0