Back to search results
Qwen3-Coder-Next · Q4_K_M
Qualcomm Snapdragon 7 Gen 4Ollama v0.27L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q4_K_M) on Qualcomm Snapdragon 7 Gen 4 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
32.69 tok/s
Decode
Decode speed
144.19 tok/s
Prefill
Prefill speed
2.22 s
TTFT
Time to first token
1.05 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 · IQ1_S Decode 53.91 · Prefill 278.28 ·
- Ollama · IQ3_S Decode 37.55 · Prefill 185.53 ·
- Ollama · Q4_K_M (current)Decode 32.69 · Prefill 144.19 ·
Core figures
- Decode (avg)
- 32.69 tok/s
- Prefill (avg)
- 144.19 tok/s
- TTFT (avg)
- 2.22 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- —
- TTFB
- 0.26 GB
- Power draw
- 8.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Coder-Next
- Quantization
- Q4_K_M
- Framework
- Ollama
- Version
- v0.27
- Context length
- 8192 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
- Qualcomm Snapdragon 7 Gen 4
- Measured VRAM (avg)
- 1.05 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 8.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · Windows 11 23H2 · CUDA N/A · 8192 ctx
32.69 tok/s
Decode
144.19 tok/s
Prefill
2.22 s
TTFT
1.05 GB
VRAM
—
MTP
8.9 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=105 running model_id=58 at Q4_K_M