Back to search results
Qwen3-Embedding-0.6B · Q4_K_S
AMD Radeon RX 9070 XT16GBllama.cpp v0.36L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q4_K_S) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
280.71 tok/s
Decode
Decode speed
1,416.08 tok/s
Prefill
Prefill speed
0.9 s
TTFT
Time to first token
3.09 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_S Decode 308.65 · Prefill 1242.43 ·
- llama.cpp · Q4_K_S (current)Decode 280.71 · Prefill 1416.08 ·
- vLLM · IQ1_S Decode 320.75 · Prefill 1355.61 ·
- vLLM · Q5_K_M Decode 254.02 · Prefill 1313.89 ·
Core figures
- Decode (avg)
- 280.71 tok/s
- Prefill (avg)
- 1,416.08 tok/s
- TTFT (avg)
- 0.9 s
- VRAM (avg)
- 3.09 GB
- MTP acceptance rate
- —
- TTFB
- 2.25 GB
- Power draw
- 249.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q4_K_S
- Framework
- llama.cpp
- Version
- v0.36
- 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 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 3.09 GB
- OS
- Ubuntu 22.04
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 249.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.36 · Ubuntu 22.04 · CUDA N/A · 16384 ctx
280.71 tok/s
Decode
1,416.08 tok/s
Prefill
0.9 s
TTFT
3.09 GB
VRAM
—
MTP
249.9 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=16 running model_id=62 at Q4_K_S