Back to search results
Qwen3-Coder-Next · Q3_K_M
NVIDIA RTX 509032GBOllama v0.36L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q3_K_M) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
238.15 tok/s
Decode
Decode speed
870.24 tok/s
Prefill
Prefill speed
0.86 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 (current)Decode 238.15 · Prefill 870.24 ·
- Strata · IQ1_S 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)
- 238.15 tok/s
- Prefill (avg)
- 870.24 tok/s
- TTFT (avg)
- 0.86 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- —
- TTFB
- 1.91 GB
- Power draw
- 358.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Coder-Next
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.36
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 99
- 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
- 12.4
- Power draw
- 358.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.36 · macOS 15.0 · CUDA 12.4 · 16384 ctx
238.15 tok/s
Decode
870.24 tok/s
Prefill
0.86 s
TTFT
1.05 GB
VRAM
—
MTP
358.7 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=13 running model_id=58 at Q3_K_M