Back to search results
Qwen3-4B-Thinking-2507 · IQ2_XS
AMD Strix Halo (Radeon 8060S)Strata v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (IQ2_XS) on AMD Strix Halo (Radeon 8060S) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
206.18 tok/s
Decode
Decode speed
1,005.37 tok/s
Prefill
Prefill speed
1.09 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
2 days ago
Last verified
Performance
- llama.cpp · Q3_K_S Decode 117.04 · Prefill 404.22 ·
- llama.cpp · Q5_K_M Decode 77.99 · Prefill 423.17 ·
- Strata · IQ2_XS (current)Decode 206.18 · Prefill 1005.37 ·
- Strata · IQ3_S Decode 166.26 · Prefill 669.87 ·
Core figures
- Decode (avg)
- 206.18 tok/s
- Prefill (avg)
- 1,005.37 tok/s
- TTFT (avg)
- 1.09 s
- VRAM (avg)
- 6.13 GB
- MTP acceptance rate
- 0.63
- TTFB
- 1.65 GB
- Power draw
- 52.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- IQ2_XS
- Framework
- Strata
- Version
- v0.47
- Context length
- 4096 tokens
- Batch size
- 1024
- GPU layers
- 8
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Strix Halo (Radeon 8060S)
- Measured VRAM (avg)
- 6.13 GB
- OS
- Ubuntu 22.04
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 52.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · Ubuntu 22.04 · CUDA N/A · 4096 ctx
206.18 tok/s
Decode
1,005.37 tok/s
Prefill
1.09 s
TTFT
6.13 GB
VRAM
0.63
MTP
52.1 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=87 running model_id=57 at IQ2_XS