Back to search results
Qwen3-1.7B · IQ3_XS
AMD Radeon RX 7900 XTX24GBllama.cpp v0.27L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (IQ3_XS) on AMD Radeon RX 7900 XTX with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
234.47 tok/s
Decode
Decode speed
1,079.52 tok/s
Prefill
Prefill speed
2.39 s
TTFT
Time to first token
4.32 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ3_XS (current)Decode 234.47 · Prefill 1079.52 ·
- llama.cpp · Q4_K_M Decode 178.72 · Prefill 842.7 ·
- Ollama · Q3_K_M Decode 196.24 · Prefill 705.31 ·
- Ollama · Q8_0 Decode 111.35 · Prefill 362.65 ·
- Strata · Q4_K_S Decode 249 · Prefill 1211.72 ·
Core figures
- Decode (avg)
- 234.47 tok/s
- Prefill (avg)
- 1,079.52 tok/s
- TTFT (avg)
- 2.39 s
- VRAM (avg)
- 4.32 GB
- MTP acceptance rate
- —
- TTFB
- 1.88 GB
- Power draw
- 461 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- IQ3_XS
- Framework
- llama.cpp
- Version
- v0.27
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Radeon RX 7900 XTX
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 4.32 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 461 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · Windows 11 23H2 · CUDA 12.8 · 2048 ctx
234.47 tok/s
Decode
1,079.52 tok/s
Prefill
2.39 s
TTFT
4.32 GB
VRAM
—
MTP
461 W
Power draw
L2 batch seed 2026-10-10: llama.cpp on hw_id=11 running model_id=55 at IQ3_XS