Back to search results
Qwen2.5-0.5B-Instruct · Q5_K_S
AMD Radeon RX 9070 XT16GBllama.cpp v0.28L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q5_K_S) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
267.22 tok/s
Decode
Decode speed
915.84 tok/s
Prefill
Prefill speed
0.66 s
TTFT
Time to first token
3.04 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 · Q5_K_S (current)Decode 267.22 · Prefill 915.84 ·
- Strata · IQ2_M Decode 311.28 · Prefill 1001.12 ·
- Strata · IQ3_S Decode 358.46 · Prefill 1486.41 ·
Core figures
- Decode (avg)
- 267.22 tok/s
- Prefill (avg)
- 915.84 tok/s
- TTFT (avg)
- 0.66 s
- VRAM (avg)
- 3.04 GB
- MTP acceptance rate
- —
- TTFB
- 2.14 GB
- Power draw
- 271.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- Q5_K_S
- Framework
- llama.cpp
- Version
- v0.28
- Context length
- 32768 tokens
- Batch size
- 256
- 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 9070 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 3.04 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 271.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.28 · macOS 15.0 · CUDA N/A · 32768 ctx
267.22 tok/s
Decode
915.84 tok/s
Prefill
0.66 s
TTFT
3.04 GB
VRAM
—
MTP
271.1 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=16 running model_id=59 at Q5_K_S