Back to search results
Qwen3-4B-Thinking-2507 · Q4_K_S
Intel Arc 140VOllama v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q4_K_S) on Intel Arc 140V with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
56.88 tok/s
Decode
Decode speed
225.68 tok/s
Prefill
Prefill speed
0.98 s
TTFT
Time to first token
8.65 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 77.55 · Prefill 286.29 ·
- Ollama · Q4_K_S (current)Decode 56.88 · Prefill 225.68 ·
Core figures
- Decode (avg)
- 56.88 tok/s
- Prefill (avg)
- 225.68 tok/s
- TTFT (avg)
- 0.98 s
- VRAM (avg)
- 8.65 GB
- MTP acceptance rate
- —
- TTFB
- 0.46 GB
- Power draw
- 191.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- Q4_K_S
- Framework
- Ollama
- Version
- v0.21
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Intel Arc 140V
- Measured VRAM (avg)
- 8.65 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 191.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx
56.88 tok/s
Decode
225.68 tok/s
Prefill
0.98 s
TTFT
8.65 GB
VRAM
—
MTP
191.2 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=98 running model_id=57 at Q4_K_S