Back to search results
Qwen3-4B · Q2_K
AMD Radeon RX 907016GBllama.cpp v0.28L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q2_K) on AMD Radeon RX 9070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
140.23 tok/s
Decode
Decode speed
653.54 tok/s
Prefill
Prefill speed
2.23 s
TTFT
Time to first token
6.72 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 · Q2_K (current)Decode 140.23 · Prefill 653.54 ·
- llama.cpp · Q8_0 Decode 73.3 · Prefill 246.97 ·
- Strata · IQ4_XS Decode 168.75 · Prefill 844.33 ·
Core figures
- Decode (avg)
- 140.23 tok/s
- Prefill (avg)
- 653.54 tok/s
- TTFT (avg)
- 2.23 s
- VRAM (avg)
- 6.72 GB
- MTP acceptance rate
- —
- TTFB
- 1.12 GB
- Power draw
- 240.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q2_K
- Framework
- llama.cpp
- Version
- v0.28
- Context length
- 16384 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 9070
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 6.72 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 240.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.28 · macOS 15.0 · CUDA N/A · 16384 ctx
140.23 tok/s
Decode
653.54 tok/s
Prefill
2.23 s
TTFT
6.72 GB
VRAM
—
MTP
240.2 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=21 running model_id=54 at Q2_K