Back to search results
Qwen3.5-0.8B · IQ2_XS
AMD Radeon RX 7900 XTX24GBllama.cpp v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_XS) on AMD Radeon RX 7900 XTX with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
280.58 tok/s
Decode
Decode speed
1,056.43 tok/s
Prefill
Prefill speed
1.71 s
TTFT
Time to first token
2.91 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · IQ2_XS (current)Decode 280.58 · Prefill 1056.43 ·
- Ollama · Q4_K_M Decode 171.2 · Prefill 687.99 ·
- Ollama · Q5_K_S Decode 148.35 · Prefill 573.18 ·
- Strata · Q4_K_S Decode 289.51 · Prefill 1525.63 ·
- llama.cpp · Q3_K_M Decode 251.67 · Prefill 1158.4 ·
- vLLM · IQ3_XS Decode 312.18 · Prefill 1202.88 ·
- vLLM · Q6_K Decode 198.86 · Prefill 984.35 ·
Core figures
- Decode (avg)
- 280.58 tok/s
- Prefill (avg)
- 1,056.43 tok/s
- TTFT (avg)
- 1.71 s
- VRAM (avg)
- 2.91 GB
- MTP acceptance rate
- —
- TTFB
- 2.24 GB
- Power draw
- 231.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ2_XS
- Framework
- llama.cpp
- Version
- v0.33
- Context length
- 4096 tokens
- Batch size
- 512
- 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)
- 2.91 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu 6.11
- CUDA
- 12.6
- Power draw
- 231.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · Windows 11 23H2 · CUDA 12.6 · 4096 ctx
280.58 tok/s
Decode
1,056.43 tok/s
Prefill
1.71 s
TTFT
2.91 GB
VRAM
—
MTP
231.2 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=11 running model_id=51 at IQ2_XS