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/Magistral Small 2507/on AMD Instinct MI100 32GB

Can it run?

Can AMD Instinct MI100 32GB run Magistral Small 2507?

BGood

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

54.5 tok/s

TTFT

3551 ms

Safe context

22K

Memory

22.8 GB / 32.0 GB

Memory breakdown

Weights14.6 GB
KV Cache3.8 GB
Runtime1.2 GB
Headroom3.2 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCTight fit54.5 tok/s5165 ms39K
ChatCRuns well54.5 tok/s1937 ms12K
CodingBRuns well54.5 tok/s3551 ms22K
RAGCTight fit54.5 tok/s6456 ms39K
ReasoningBRuns well54.5 tok/s4196 ms22K

Quantization options

How Magistral Small 2507 (24B params) fits at each quantization level on AMD Instinct MI100 32GB (32.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
9.4 GB
LowD36
Q3_K_S
3
11.8 GB
LowD37
NVFP4
4
13.4 GB
MediumD38
Q4_K_M
4
14.6 GB
MediumD39
Q5_K_M
5
17.3 GB
HighC41
Q6_K
6
19.7 GB
HighC42
Q8_0Best for your GPU
8
25.7 GB
Very HighC44
F16
16
49.2 GB
MaximumF0

Get started

Ollama
ollama run magistral-small-2507
HuggingFace
huggingface-cli download magistral-small-2507
See all results for AMD Instinct MI100 32GBSee all hardware for Magistral Small 2507