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 2 123B Instruct/on AMD Instinct MI350X 288GB

Can it run?

Can AMD Instinct MI350X 288GB run Devstral 2 123B Instruct?

CUsable

Runs well

Using Q4_K_M in vLLM

Capabilities:

Fit status

Runs well

Decode

77.8 tok/s

TTFT

2487 ms

Safe context

37K

Memory

125.4 GB / 288.0 GB

Memory breakdown

Weights75.0 GB
KV Cache19.2 GB
Runtime2.4 GB
Headroom28.8 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCRuns well77.8 tok/s3618 ms64K
ChatCRuns well77.8 tok/s1357 ms20K
CodingCRuns well77.8 tok/s2487 ms37K
RAGCRuns well77.8 tok/s4522 ms64K
ReasoningCRuns well77.8 tok/s2940 ms37K

Quantization options

How Devstral 2 123B Instruct (123B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
48.0 GB
LowD33
Q3_K_S
3
60.3 GB
LowD34
NVFP4
4
68.9 GB
MediumD35
Q4_K_M
4
75.0 GB
MediumD35
Q5_K_M
5
88.6 GB
HighD36
Q6_K
6
100.9 GB
HighD37
Q8_0Best for your GPU
8
131.6 GB
Very HighD39
F16
16
252.2 GB
MaximumC45

Get started

HuggingFace
huggingface-cli download devstral-2-123b
See all results for AMD Instinct MI350X 288GBSee all hardware for Devstral 2 123B Instruct