Back to search results
Qwen3-8B · Q2_K
NVIDIA RTX 309024GBOllama v0.32L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q2_K) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
98.87 tok/s
Decode
Decode speed
381.75 tok/s
Prefill
Prefill speed
0.26 s
TTFT
Time to first token
11.34 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- vLLM · IQ2_XS Decode 113.39 · Prefill 440.93 ·
- Ollama · Q2_K (current)Decode 98.87 · Prefill 381.75 ·
- vLLM · IQ3_XS Decode 108.64 · Prefill 552.19 ·
- Ollama · IQ4_XS Decode 96.65 · Prefill 382.18 ·
- Ollama · Q8_0 Decode 48.02 · Prefill 169.17 ·
- Strata · Q5_K_S Decode 138.04 · Prefill 495.5 ·
- llama.cpp · Q8_0 Decode 84.9 · Prefill 636.8 ·
- llama.cpp · Q5_K_M Decode 123.7 · Prefill 927.8 ·
- llama.cpp · Q4_K_M Decode 149 · Prefill 1117.5 ·
Core figures
- Decode (avg)
- 98.87 tok/s
- Prefill (avg)
- 381.75 tok/s
- TTFT (avg)
- 0.26 s
- VRAM (avg)
- 11.34 GB
- MTP acceptance rate
- —
- TTFB
- 0.79 GB
- Power draw
- 326.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q2_K
- Framework
- Ollama
- Version
- v0.32
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 11.34 GB
- OS
- Windows 11 24H2
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 326.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.32 · Windows 11 24H2 · CUDA 12.6 · 16384 ctx
98.87 tok/s
Decode
381.75 tok/s
Prefill
0.26 s
TTFT
11.34 GB
VRAM
—
MTP
326.3 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=2 running model_id=53 at Q2_K