Back to search results
Qwen3.5-9B · Q4_K_S
AMD Radeon RX 7800 XT16GBOllama v0.29L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (Q4_K_S) on AMD Radeon RX 7800 XT with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
72.3 tok/s
Decode
Decode speed
388.61 tok/s
Prefill
Prefill speed
1.81 s
TTFT
Time to first token
15.2 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 Decode 90.06 · Prefill 377.76 ·
- Ollama · Q4_K_S (current)Decode 72.3 · Prefill 388.61 ·
Core figures
- Decode (avg)
- 72.3 tok/s
- Prefill (avg)
- 388.61 tok/s
- TTFT (avg)
- 1.81 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.58 GB
- Power draw
- 240.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- Q4_K_S
- Framework
- Ollama
- Version
- v0.29
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 99
- Flash Attention
- Off
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)
- 15.2 GB
- OS
- macOS 15.0
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 240.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.29 · macOS 15.0 · CUDA N/A · 2048 ctx
72.3 tok/s
Decode
388.61 tok/s
Prefill
1.81 s
TTFT
15.2 GB
VRAM
—
MTP
240.5 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=31 running model_id=49 at Q4_K_S