Back to search results
Qwen3-4B · Q4_K_M
2x AMD Strix HaloOllama v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q4_K_M) on 2x AMD Strix Halo with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
165.67 tok/s
Decode
Decode speed
892.04 tok/s
Prefill
Prefill speed
1.64 s
TTFT
Time to first token
8.99 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · FP16 Decode 87.02 · Prefill 443.84 ·
- Ollama · IQ3_S Decode 197.15 · Prefill 955.03 ·
- Ollama · Q4_K_M (current)Decode 165.67 · Prefill 892.04 ·
Core figures
- Decode (avg)
- 165.67 tok/s
- Prefill (avg)
- 892.04 tok/s
- TTFT (avg)
- 1.64 s
- VRAM (avg)
- 8.99 GB
- MTP acceptance rate
- —
- TTFB
- 1.33 GB
- Power draw
- 72.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q4_K_M
- Framework
- Ollama
- Version
- v0.40
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- 2x AMD Strix Halo
- Measured VRAM (avg)
- 8.99 GB
- OS
- Ubuntu 22.04
- Driver
- 555.85
- CUDA
- N/A
- Power draw
- 72.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · Ubuntu 22.04 · CUDA N/A · 32768 ctx
165.67 tok/s
Decode
892.04 tok/s
Prefill
1.64 s
TTFT
8.99 GB
VRAM
—
MTP
72.1 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=88 running model_id=54 at Q4_K_M