Back to search results
Qwen3-Coder-Next · IQ2_M
Qualcomm Snapdragon X EliteOllama v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ2_M) on Qualcomm Snapdragon X Elite with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
54.16 tok/s
Decode
Decode speed
255.41 tok/s
Prefill
Prefill speed
1.29 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 · Q3_K_L Decode 48.96 · Prefill 229.97 ·
- Ollama · IQ2_M (current)Decode 54.16 · Prefill 255.41 ·
Core figures
- Decode (avg)
- 54.16 tok/s
- Prefill (avg)
- 255.41 tok/s
- TTFT (avg)
- 1.29 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- —
- TTFB
- 0.43 GB
- Power draw
- 14.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Coder-Next
- Quantization
- IQ2_M
- Framework
- Ollama
- Version
- v0.43
- Context length
- 2048 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
- Qualcomm Snapdragon X Elite
- Measured VRAM (avg)
- 1.05 GB
- OS
- Windows 11 23H2
- Driver
- Qualcomm Adreno 7.0
- CUDA
- N/A
- Power draw
- 14.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · Windows 11 23H2 · CUDA N/A · 2048 ctx
54.16 tok/s
Decode
255.41 tok/s
Prefill
1.29 s
TTFT
1.05 GB
VRAM
—
MTP
14.5 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=104 running model_id=58 at IQ2_M