Will It Run AI
CalculatorModelsHardwareCompare
Product
  • Calculator
  • Compare
  • Tier List
Browse
  • Models
  • Hardware
  • Docs
About
  • Why It Works
  • What's New
  • Legal Notice
  • Privacy Policy

All estimates are approximations based on mathematical models and public specifications. Actual performance may vary. Do not make purchasing decisions based solely on these estimates.

Data sourced from Hugging Face, Ollama, and official model documentation. Model names and logos are trademarks of their respective owners.

© 2026 Will It Run AI — Fase Consulting Ibiza, S.L. (NIF: B57969656)

Home/Devstral Small 2 24B Instruct/on AMD Instinct MI325X 256GB

Can it run?

Can AMD Instinct MI325X 256GB run Devstral Small 2 24B Instruct?

CUsable

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

299.2 tok/s

TTFT

647 ms

Safe context

91K

Memory

45.2 GB / 256.0 GB

Memory breakdown

Weights14.6 GB
KV Cache3.8 GB
Runtime1.2 GB
Headroom25.6 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCRuns well299.2 tok/s941 ms167K
ChatCRuns well299.2 tok/s353 ms47K
CodingCRuns well299.2 tok/s647 ms91K
RAGCRuns well299.2 tok/s1177 ms167K
ReasoningCRuns well299.2 tok/s765 ms91K

Quantization options

How Devstral Small 2 24B Instruct (24B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
9.4 GB
LowD30
Q3_K_S
3
11.8 GB
LowD30
NVFP4
4
13.4 GB
MediumD31
Q4_K_M
4
14.6 GB
MediumD31
Q5_K_M
5
17.3 GB
HighD31
Q6_K
6
19.7 GB
HighD31
Q8_0
8
25.7 GB
Very HighD32
F16Best for your GPU
16
49.2 GB
MaximumD34

Get started

Ollama
ollama run devstral-small-2-24b
HuggingFace
huggingface-cli download devstral-small-2-24b
See all results for AMD Instinct MI325X 256GBSee all hardware for Devstral Small 2 24B Instruct