Back to search results
Qwen3-Coder-Next · IQ1_S
NVIDIA RTX 509032GBStrata v0.49L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ1_S) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
320.16 tok/s
Decode
Decode speed
1,259.65 tok/s
Prefill
Prefill speed
1.47 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
- Ollama · IQ2_M Decode 299.22 · Prefill 1242.06 ·
- Ollama · Q3_K_M Decode 238.15 · Prefill 870.24 ·
- Strata · IQ1_S (current)Decode 320.16 · Prefill 1259.65 ·
- vLLM · Q5_K_M Decode — · Prefill — ·
- vLLM · Q4_K_M Decode — · Prefill — ·
- llama.cpp · Q5_K_M Decode — · Prefill — ·
- llama.cpp · Q4_K_M Decode — · Prefill — ·
Core figures
- Decode (avg)
- 320.16 tok/s
- Prefill (avg)
- 1,259.65 tok/s
- TTFT (avg)
- 1.47 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- 0.69
- TTFB
- 2.56 GB
- Power draw
- 389.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Coder-Next
- Quantization
- IQ1_S
- Framework
- Strata
- Version
- v0.49
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 12
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 1.05 GB
- OS
- macOS 15.0
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 389.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.49 · macOS 15.0 · CUDA 12.8 · 16384 ctx
320.16 tok/s
Decode
1,259.65 tok/s
Prefill
1.47 s
TTFT
1.05 GB
VRAM
0.69
MTP
389.9 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=13 running model_id=58 at IQ1_S