Hailo-10H (Pi AI HAT+ 2) Qwen2.5-Coder-1.5B compiled-model TPS
8.13 tokens/sec compiled-model TPS (Hailo-Ollama on HailoRT)
Fields
id
benchmarks/comm-hailo10h-pi-ai-hat2-qwen25-coder-1p5b-tpsMetric
decode_tok_s
Value
8.13
Unit
tokens/sec compiled-model TPS (Hailo-Ollama on HailoRT)
Model
Qwen2.5-Coder-1.5B
Methodology
Vendor compiled-model TPS table (hailo_model_zoo_genai MODELS.rst); single-stream class figure, batch-1 Ollama-compatible server
Measured by
vendor
Thermal state
unknown
notes
VENDOR COMPILED-MODEL TABLE. Ceiling is ~2B params - the HAT+2 cannot run 7B+.
Notes
VENDOR COMPILED-MODEL TABLE. Ceiling is ~2B params - the HAT+2 cannot run 7B+.