Back to search results
Llama-3.2-3B-Instruct · Q6_K
NVIDIA RTX 3060 12GB12GBStrata v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q6_K) on NVIDIA RTX 3060 12GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
168.05 tok/s
Decode
Decode speed
844.89 tok/s
Prefill
Prefill speed
0.6 s
TTFT
Time to first token
8.4 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- vLLM · Q4_K_S Decode 182.86 · Prefill 651.97 ·
- vLLM · Q5_K_S Decode 145.02 · Prefill 478.55 ·
- Strata · Q6_K (current)Decode 168.05 · Prefill 844.89 ·
- llama.cpp · IQ3_S Decode 193.44 · Prefill 733.2 ·
- llama.cpp · Q5_K_S Decode 126.84 · Prefill 630.8 ·
- vLLM · Q5_K_M Decode 143.38 · Prefill 521.02 ·
- llama.cpp · Q8_0 Decode 87.8 · Prefill 658.5 ·
- llama.cpp · Q5_K_M Decode 127.6 · Prefill 957 ·
- llama.cpp · Q4_K_M Decode 156 · Prefill 1170 ·
Core figures
- Decode (avg)
- 168.05 tok/s
- Prefill (avg)
- 844.89 tok/s
- TTFT (avg)
- 0.6 s
- VRAM (avg)
- 8.4 GB
- MTP acceptance rate
- 0.77
- TTFB
- 1.34 GB
- Power draw
- 147.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.2-3B-Instruct
- Quantization
- Q6_K
- Framework
- Strata
- Version
- v0.44
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 5
- 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)
- 8.4 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 147.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · Windows 11 23H2 · CUDA 12.8 · 8192 ctx
168.05 tok/s
Decode
844.89 tok/s
Prefill
0.6 s
TTFT
8.4 GB
VRAM
0.77
MTP
147.2 W
Power draw
L2 batch seed 2026-10-19: Strata on hw_id=15 running model_id=70 at Q6_K