Back to search results
Qwen3-1.7B · Q2_K
NVIDIA RTX 509032GBStrata v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q2_K) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
300.65 tok/s
Decode
Decode speed
1,243.6 tok/s
Prefill
Prefill speed
1.51 s
TTFT
Time to first token
4.06 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q5_K_M Decode 353.77 · Prefill 1906.09 ·
- llama.cpp · Q6_K Decode 345.13 · Prefill 1779.25 ·
- Ollama · FP16 Decode 199.27 · Prefill 1057.11 ·
- Strata · Q2_K (current)Decode 300.65 · Prefill 1243.6 ·
- Strata · Q4_K_M Decode 280.21 · Prefill 1416.33 ·
Core figures
- Decode (avg)
- 300.65 tok/s
- Prefill (avg)
- 1,243.6 tok/s
- TTFT (avg)
- 1.51 s
- VRAM (avg)
- 4.06 GB
- MTP acceptance rate
- 0.45
- TTFB
- 2.41 GB
- Power draw
- 512.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q2_K
- Framework
- Strata
- Version
- v0.35
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 12
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 4.06 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 512.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · Windows 11 23H2 · CUDA 12.8 · 8192 ctx
300.65 tok/s
Decode
1,243.6 tok/s
Prefill
1.51 s
TTFT
4.06 GB
VRAM
0.45
MTP
512.1 W
Power draw
L2 batch seed 2026-10-10: Strata on hw_id=13 running model_id=55 at Q2_K