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/Qwen 2.5 72B/on AMD Instinct MI300A 128GB

Can it run?

Can AMD Instinct MI300A 128GB run Qwen 2.5 72B?

CUsable

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

84.5 tok/s

TTFT

2292 ms

Safe context

30K

Memory

69.2 GB / 128.0 GB

Memory breakdown

Weights43.9 GB
KV Cache11.3 GB
Runtime1.2 GB
Headroom12.8 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingBRuns well84.5 tok/s3334 ms51K
ChatCRuns well84.5 tok/s1250 ms16K
CodingCRuns well84.5 tok/s2292 ms30K
RAGBRuns well84.5 tok/s4167 ms51K
ReasoningCRuns well84.5 tok/s2709 ms30K

Quantization options

How Qwen 2.5 72B (72B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
28.1 GB
LowD34
Q3_K_S
3
35.3 GB
LowD35
NVFP4
4
40.3 GB
MediumD36
Q4_K_M
4
43.9 GB
MediumD37
Q5_K_M
5
51.8 GB
HighD38
Q6_K
6
59.0 GB
HighD39
Q8_0Best for your GPU
8
77.0 GB
Very HighC42
F16
16
147.6 GB
MaximumF0

Get started

Ollama
ollama run qwen-2.5-72b
HuggingFace
huggingface-cli download qwen-2.5-72b
See all results for AMD Instinct MI300A 128GBSee all hardware for Qwen 2.5 72B