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/Qwen2.5 1.5B Instruct/on AMD Instinct MI210 64GB

Can it run?

Can AMD Instinct MI210 64GB run Qwen2.5 1.5B Instruct?

CUsable

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

1113.8 tok/s

TTFT

350 ms

Safe context

110K

Memory

9.3 GB / 64.0 GB

Memory breakdown

Weights0.9 GB
KV Cache0.8 GB
Runtime1.2 GB
Headroom6.4 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCRuns well1113.8 tok/s350 ms220K
ChatCRuns well1113.8 tok/s350 ms55K
CodingCRuns well1113.8 tok/s350 ms110K
RAGCRuns well1113.8 tok/s350 ms220K
ReasoningCRuns well1113.8 tok/s350 ms110K

Quantization options

How Qwen2.5 1.5B Instruct (1.5B params) fits at each quantization level on AMD Instinct MI210 64GB (64.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
0.6 GB
LowD30
Q3_K_S
3
0.7 GB
LowD30
NVFP4
4
0.8 GB
MediumD30
Q4_K_M
4
0.9 GB
MediumD30
Q5_K_M
5
1.1 GB
HighD30
Q6_K
6
1.2 GB
HighD30
Q8_0
8
1.6 GB
Very HighD30
F16Best for your GPU
16
3.1 GB
MaximumD30

Get started

Upgrade options

Hardware that runs Qwen2.5 1.5B Instruct well

AppleMacBook Pro M4 Max 96GBBudget pick
C344 tok/s decode

~$2,499 MSRP

AppleMacBook Pro M3 Max 128GBBest value
C240 tok/s decode

~$2,499 MSRP

AppleMacBook Pro M2 Max 96GBBiggest leap
C232 tok/s decode

~$3,199 MSRP

See all results for AMD Instinct MI210 64GBSee all hardware for Qwen2.5 1.5B Instruct