Back to search results
Qwen3-4B-Thinking-2507 · IQ2_XS
NVIDIA RTX 407012GBStrata v0.41L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (IQ2_XS) on NVIDIA RTX 4070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
167.79 tok/s
Decode
Decode speed
693.81 tok/s
Prefill
Prefill speed
1.97 s
TTFT
Time to first token
6.13 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · Q5_K_S Decode 75.85 · Prefill 366.79 ·
- Strata · IQ2_XS (current)Decode 167.79 · Prefill 693.81 ·
- Strata · IQ4_XS Decode 136.2 · Prefill 500.55 ·
Core figures
- Decode (avg)
- 167.79 tok/s
- Prefill (avg)
- 693.81 tok/s
- TTFT (avg)
- 1.97 s
- VRAM (avg)
- 6.13 GB
- MTP acceptance rate
- 0.74
- TTFB
- 1.34 GB
- Power draw
- 221 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- IQ2_XS
- Framework
- Strata
- Version
- v0.41
- Context length
- 4096 tokens
- Batch size
- 1024
- GPU layers
- 15
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4070
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 6.13 GB
- OS
- Ubuntu 22.04
- Driver
- 555.85
- CUDA
- 12.6
- Power draw
- 221 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.41 · Ubuntu 22.04 · CUDA 12.6 · 4096 ctx
167.79 tok/s
Decode
693.81 tok/s
Prefill
1.97 s
TTFT
6.13 GB
VRAM
0.74
MTP
221 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=45 running model_id=57 at IQ2_XS