Back to search results
Qwen3.5-4B · Q5_K_S
Intel Arc A770 16GB16GBOllama v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q5_K_S) on Intel Arc A770 16GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
56.42 tok/s
Decode
Decode speed
256.71 tok/s
Prefill
Prefill speed
1.63 s
TTFT
Time to first token
9.66 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q3_K_M Decode 77.24 · Prefill 250.09 ·
- vLLM · Q4_K_M Decode 74.79 · Prefill 395.91 ·
- Ollama · Q2_K Decode 90.54 · Prefill 350.46 ·
- Ollama · Q5_K_S (current)Decode 56.42 · Prefill 256.71 ·
- llama.cpp · Q3_K_M Decode 75.53 · Prefill 384.12 ·
- llama.cpp · Q4_K_M Decode 65.4 · Prefill 252.99 ·
- vLLM · Q3_K_L Decode 82.73 · Prefill 332.62 ·
- vLLM · Q8_0 Decode 45.45 · Prefill 151.34 ·
Core figures
- Decode (avg)
- 56.42 tok/s
- Prefill (avg)
- 256.71 tok/s
- TTFT (avg)
- 1.63 s
- VRAM (avg)
- 9.66 GB
- MTP acceptance rate
- —
- TTFB
- 0.45 GB
- Power draw
- 198 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q5_K_S
- Framework
- Ollama
- Version
- v0.26
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Intel Arc A770 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 9.66 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 198 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx
56.42 tok/s
Decode
256.71 tok/s
Prefill
1.63 s
TTFT
9.66 GB
VRAM
—
MTP
198 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=97 running model_id=48 at Q5_K_S