Back to search results
gemma-4-E4B-it · Q6_K
AMD Strix Point (Radeon 890M)vLLM v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-E4B-it (Q6_K) on AMD Strix Point (Radeon 890M) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
56.27 tok/s
Decode
Decode speed
255.06 tok/s
Prefill
Prefill speed
1.64 s
TTFT
Time to first token
10.5 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ3_XS Decode 93.71 · Prefill 479.79 ·
- vLLM · Q6_K (current)Decode 56.27 · Prefill 255.06 ·
- Ollama · Q2_K Decode 85.31 · Prefill 404.47 ·
Core figures
- Decode (avg)
- 56.27 tok/s
- Prefill (avg)
- 255.06 tok/s
- TTFT (avg)
- 1.64 s
- VRAM (avg)
- 10.5 GB
- MTP acceptance rate
- —
- TTFB
- 0.45 GB
- Power draw
- 58.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-E4B-it
- Quantization
- Q6_K
- Framework
- vLLM
- Version
- v0.43
- Context length
- 2048 tokens
- Batch size
- 8
- GPU layers
- 999
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Strix Point (Radeon 890M)
- Measured VRAM (avg)
- 10.5 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 58.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · macOS 15.0 · CUDA N/A · 2048 ctx
56.27 tok/s
Decode
255.06 tok/s
Prefill
1.64 s
TTFT
10.5 GB
VRAM
—
MTP
58.1 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=89 running model_id=67 at Q6_K