Back to search results
Qwen3.5-9B · IQ3_XS
AMD Radeon RX 7800 XT16GBllama.cpp v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (IQ3_XS) on AMD Radeon RX 7800 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
90.06 tok/s
Decode
Decode speed
377.76 tok/s
Prefill
Prefill speed
0.32 s
TTFT
Time to first token
13.82 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ3_XS (current)Decode 90.06 · Prefill 377.76 ·
- Ollama · Q4_K_S Decode 72.3 · Prefill 388.61 ·
Core figures
- Decode (avg)
- 90.06 tok/s
- Prefill (avg)
- 377.76 tok/s
- TTFT (avg)
- 0.32 s
- VRAM (avg)
- 13.82 GB
- MTP acceptance rate
- —
- TTFB
- 0.72 GB
- Power draw
- 298.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- IQ3_XS
- Framework
- llama.cpp
- Version
- v0.54
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 28
- 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 7800 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 13.82 GB
- OS
- Ubuntu 22.04
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 298.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Ubuntu 22.04 · CUDA N/A · 8192 ctx
90.06 tok/s
Decode
377.76 tok/s
Prefill
0.32 s
TTFT
13.82 GB
VRAM
—
MTP
298.8 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=31 running model_id=49 at IQ3_XS