Back to search results
Qwen3.5-4B · IQ2_M
NVIDIA RTX 3060 12GB12GBOllama v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (IQ2_M) on NVIDIA RTX 3060 12GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
91.19 tok/s
Decode
Decode speed
447.34 tok/s
Prefill
Prefill speed
0.71 s
TTFT
Time to first token
6.47 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Ollama · IQ2_M (current)Decode 91.19 · Prefill 447.34 ·
- Ollama · Q4_K_M Decode 66.59 · Prefill 338.55 ·
- llama.cpp · IQ3_S Decode 105.18 · Prefill 415.05 ·
- Ollama · IQ3_S Decode 95.65 · Prefill 519.99 ·
- Ollama · Q3_K_M Decode 97.19 · Prefill 407.59 ·
- Strata · Q5_K_S Decode 113.91 · Prefill 618.95 ·
- Strata · Q6_K Decode 100.84 · Prefill 413.9 ·
- llama.cpp · Q4_K_M Decode 117 · Prefill 877.5 ·
Core figures
- Decode (avg)
- 91.19 tok/s
- Prefill (avg)
- 447.34 tok/s
- TTFT (avg)
- 0.71 s
- VRAM (avg)
- 6.47 GB
- MTP acceptance rate
- —
- TTFB
- 0.73 GB
- Power draw
- 167.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ2_M
- Framework
- Ollama
- Version
- v0.26
- Context length
- 32768 tokens
- Batch size
- 256
- 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 3060 12GB
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 6.47 GB
- OS
- Windows 11 24H2
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 167.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · Windows 11 24H2 · CUDA 12.6 · 32768 ctx
91.19 tok/s
Decode
447.34 tok/s
Prefill
0.71 s
TTFT
6.47 GB
VRAM
—
MTP
167.7 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=15 running model_id=48 at IQ2_M