Back to search results
Qwen3.5-0.8B · Q5_K_S
AMD Radeon RX 9070 XT16GBOllama v0.29L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q5_K_S) on AMD Radeon RX 9070 XT with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
242.84 tok/s
Decode
Decode speed
980.43 tok/s
Prefill
Prefill speed
0.55 s
TTFT
Time to first token
3.61 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q5_K_S Decode 285.41 · Prefill 1428.43 ·
- Ollama · FP16 Decode 127.98 · Prefill 427.95 ·
- Ollama · Q5_K_S (current)Decode 242.84 · Prefill 980.43 ·
- llama.cpp · Q5_K_M Decode 182.06 · Prefill 1000.27 ·
- vLLM · IQ3_S Decode 301.46 · Prefill 1013.4 ·
Core figures
- Decode (avg)
- 242.84 tok/s
- Prefill (avg)
- 980.43 tok/s
- TTFT (avg)
- 0.55 s
- VRAM (avg)
- 3.61 GB
- MTP acceptance rate
- —
- TTFB
- 1.94 GB
- Power draw
- 227.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q5_K_S
- Framework
- Ollama
- Version
- v0.29
- Context length
- 8192 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 9070 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 3.61 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu 6.12
- CUDA
- 12.8
- Power draw
- 227.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.29 · Windows 11 23H2 · CUDA 12.8 · 8192 ctx
242.84 tok/s
Decode
980.43 tok/s
Prefill
0.55 s
TTFT
3.61 GB
VRAM
—
MTP
227.1 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=16 running model_id=51 at Q5_K_S