Back to search results
Qwen3.8-9B · IQ2_M
NVIDIA RTX 4060 Ti 16GB16GBvLLM v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ2_M) on NVIDIA RTX 4060 Ti 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
110.8 tok/s
Decode
Decode speed
556.06 tok/s
Prefill
Prefill speed
1 s
TTFT
Time to first token
11.93 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ4_XS Decode 104.81 · Prefill 479.61 ·
- vLLM · Q3_K_M Decode 106.76 · Prefill 483.03 ·
- Strata · IQ2_XS Decode 182.07 · Prefill 797.96 ·
- vLLM · IQ2_M (current)Decode 110.8 · Prefill 556.06 ·
- Ollama · Q4_K_M Decode 65.8 · Prefill 285.42 ·
Core figures
- Decode (avg)
- 110.8 tok/s
- Prefill (avg)
- 556.06 tok/s
- TTFT (avg)
- 1 s
- VRAM (avg)
- 11.93 GB
- MTP acceptance rate
- —
- TTFB
- 0.89 GB
- Power draw
- 325.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ2_M
- Framework
- vLLM
- Version
- v0.24
- Context length
- 2048 tokens
- Batch size
- 32
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4060 Ti 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 11.93 GB
- OS
- Ubuntu 24.04
- Driver
- 555.85
- CUDA
- 12.4
- Power draw
- 325.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · Ubuntu 24.04 · CUDA 12.4 · 2048 ctx
110.8 tok/s
Decode
556.06 tok/s
Prefill
1 s
TTFT
11.93 GB
VRAM
—
MTP
325.7 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=3 running model_id=52 at IQ2_M