Back to search results
Qwen3-Embedding-0.6B · Q5_K_M
AMD Radeon RX 907016GBllama.cpp v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q5_K_M) on AMD Radeon RX 9070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
203.72 tok/s
Decode
Decode speed
927.46 tok/s
Prefill
Prefill speed
0.32 s
TTFT
Time to first token
3.28 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 · IQ4_XS Decode 254.94 · Prefill 1358.71 ·
- llama.cpp · Q5_K_M (current)Decode 203.72 · Prefill 927.46 ·
- Strata · Q3_K_M Decode 383.87 · Prefill 1815.17 ·
Core figures
- Decode (avg)
- 203.72 tok/s
- Prefill (avg)
- 927.46 tok/s
- TTFT (avg)
- 0.32 s
- VRAM (avg)
- 3.28 GB
- MTP acceptance rate
- —
- TTFB
- 1.63 GB
- Power draw
- 227.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q5_K_M
- Framework
- llama.cpp
- Version
- v0.35
- 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
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 3.28 GB
- OS
- Ubuntu 22.04
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 227.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · Ubuntu 22.04 · CUDA N/A · 8192 ctx
203.72 tok/s
Decode
927.46 tok/s
Prefill
0.32 s
TTFT
3.28 GB
VRAM
—
MTP
227.1 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=21 running model_id=62 at Q5_K_M