Back to search results
Qwen3-4B-Thinking-2507 · Q2_K
NVIDIA RTX 308010GBOllama v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q2_K) on NVIDIA RTX 3080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
93.59 tok/s
Decode
Decode speed
336.53 tok/s
Prefill
Prefill speed
0.5 s
TTFT
Time to first token
6.72 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · Q2_K (current)Decode 93.59 · Prefill 336.53 ·
- Ollama · Q4_K_S Decode 73.95 · Prefill 380.29 ·
- Strata · IQ3_S Decode 134.76 · Prefill 504.77 ·
Core figures
- Decode (avg)
- 93.59 tok/s
- Prefill (avg)
- 336.53 tok/s
- TTFT (avg)
- 0.5 s
- VRAM (avg)
- 6.72 GB
- MTP acceptance rate
- —
- TTFB
- 0.75 GB
- Power draw
- 275.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- Q2_K
- Framework
- Ollama
- Version
- v0.33
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3080
- Nominal VRAM
- 10 GB
- Measured VRAM (avg)
- 6.72 GB
- OS
- Ubuntu 24.04
- Driver
- 555.85
- CUDA
- 12.6
- Power draw
- 275.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx
93.59 tok/s
Decode
336.53 tok/s
Prefill
0.5 s
TTFT
6.72 GB
VRAM
—
MTP
275.5 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=44 running model_id=57 at Q2_K