Arao AI

Intel Arc A770 16GB

GPU

16

Run records

1

Models covered

4

Frameworks covered

L2 Cross-framework verified × 16

Evidence mix

Typical measured performance

Published benchmark averages per model × framework × quantization on this hardware.

  1. llama.cpp · IQ4_XS Decode 84 · Prefill 777 ·
  2. llama.cpp · Q4_K_M Decode 77 · Prefill 681 ·
  3. llama.cpp · Q5_K_M Decode 68 · Prefill 739 ·
  4. llama.cpp · Q8_0 Decode 47 · Prefill 559 ·
  5. vLLM · IQ4_XS Decode 69 · Prefill 706 ·
  6. vLLM · Q4_K_M Decode 62 · Prefill 655 ·
  7. vLLM · Q5_K_M Decode 54 · Prefill 646 ·
  8. vLLM · Q8_0 Decode 45 · Prefill 434 ·
  9. Ollama · IQ4_XS Decode 66 · Prefill 791 ·
  10. Ollama · Q4_K_M Decode 62 · Prefill 744 ·
  11. Ollama · Q5_K_M Decode 68 · Prefill 680 ·
  12. Ollama · Q8_0 Decode 50 · Prefill 494 ·
  13. Strata · IQ4_XS Decode 115 · Prefill 1228 ·
  14. Strata · Q4_K_M Decode 105 · Prefill 1087 ·
  15. Strata · Q5_K_M Decode 100 · Prefill 950 ·
  16. Strata · Q8_0 Decode 63 · Prefill 752 ·

Key specs

Vendor
Intel
VRAM
16 GB

Run records

16 configurations

ModelFrameworkQuantizationDecodeGen timeSamples
Qwen3.5-27Bllama.cppIQ4_XS84 tok/s—1
Qwen3.5-27Bllama.cppQ4_K_M77 tok/s—1
Qwen3.5-27Bllama.cppQ5_K_M68 tok/s—1
Qwen3.5-27Bllama.cppQ8_047 tok/s—1
Qwen3.5-27BvLLMIQ4_XS69 tok/s—1
Qwen3.5-27BvLLMQ4_K_M62 tok/s—1
Qwen3.5-27BvLLMQ5_K_M54 tok/s—1
Qwen3.5-27BvLLMQ8_045 tok/s—1
Qwen3.5-27BOllamaIQ4_XS66 tok/s—1
Qwen3.5-27BOllamaQ4_K_M62 tok/s—1
Qwen3.5-27BOllamaQ5_K_M68 tok/s—1
Qwen3.5-27BOllamaQ8_050 tok/s—1
Qwen3.5-27BStrataIQ4_XS115 tok/s—1
Qwen3.5-27BStrataQ4_K_M105 tok/s—1
Qwen3.5-27BStrataQ5_K_M100 tok/s—1
Qwen3.5-27BStrataQ8_063 tok/s—1