Back to search results
Qwen3-1.7B · Q4_K_M
NVIDIA RTX 509032GBStrata v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_M) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
280.21 tok/s
Decode
Decode speed
1,416.33 tok/s
Prefill
Prefill speed
1.45 s
TTFT
Time to first token
5.03 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 Decode 300.65 · Prefill 1243.6 ·
- Strata · Q4_K_M (current)Decode 280.21 · Prefill 1416.33 ·
Core figures
- Decode (avg)
- 280.21 tok/s
- Prefill (avg)
- 1,416.33 tok/s
- TTFT (avg)
- 1.45 s
- VRAM (avg)
- 5.03 GB
- MTP acceptance rate
- 0.52
- TTFB
- 2.24 GB
- Power draw
- 482.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q4_K_M
- Framework
- Strata
- Version
- v0.50
- Context length
- 32768 tokens
- Batch size
- 1024
- 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)
- 5.03 GB
- OS
- macOS 15.0
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 482.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · macOS 15.0 · CUDA 12.8 · 32768 ctx
280.21 tok/s
Decode
1,416.33 tok/s
Prefill
1.45 s
TTFT
5.03 GB
VRAM
0.52
MTP
482.2 W
Power draw
L2 batch seed 2026-10-10: Strata on hw_id=13 running model_id=55 at Q4_K_M