Back to search results
Qwen3-1.7B · Q6_K
Intel Arc B58012GBllama.cpp v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q6_K) on Intel Arc B580 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
72.12 tok/s
Decode
Decode speed
270.78 tok/s
Prefill
Prefill speed
1.43 s
TTFT
Time to first token
5.67 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ2_XS Decode 140.48 · Prefill 573.63 ·
- llama.cpp · Q6_K (current)Decode 72.12 · Prefill 270.78 ·
- vLLM · IQ3_S Decode 115.58 · Prefill 443.88 ·
- vLLM · Q3_K_M Decode 109.13 · Prefill 478.21 ·
- Strata · IQ3_S Decode 143.13 · Prefill 545.08 ·
Core figures
- Decode (avg)
- 72.12 tok/s
- Prefill (avg)
- 270.78 tok/s
- TTFT (avg)
- 1.43 s
- VRAM (avg)
- 5.67 GB
- MTP acceptance rate
- —
- TTFB
- 0.58 GB
- Power draw
- 192.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q6_K
- Framework
- llama.cpp
- Version
- v0.33
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Intel Arc B580
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 5.67 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 192.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx
72.12 tok/s
Decode
270.78 tok/s
Prefill
1.43 s
TTFT
5.67 GB
VRAM
—
MTP
192.7 W
Power draw
L2 batch seed 2026-10-10: llama.cpp on hw_id=94 running model_id=55 at Q6_K