Back to search results
Llama-3.2-3B-Instruct · Q2_K
NVIDIA RTX 309024GBllama.cpp v0.49L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q2_K) on NVIDIA RTX 3090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
268 tok/s
Decode
Decode speed
1,209.31 tok/s
Prefill
Prefill speed
2.46 s
TTFT
Time to first token
5.57 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q2_K (current)Decode 268 · Prefill 1209.31 ·
- Strata · FP16 Decode 145.3 · Prefill 693.51 ·
- llama.cpp · Q8_0 Decode 228.2 · Prefill 1711.5 ·
- llama.cpp · Q5_K_M Decode 331.9 · Prefill 2489.3 ·
- llama.cpp · Q4_K_M Decode 405.6 · Prefill 3042 ·
Core figures
- Decode (avg)
- 268 tok/s
- Prefill (avg)
- 1,209.31 tok/s
- TTFT (avg)
- 2.46 s
- VRAM (avg)
- 5.57 GB
- MTP acceptance rate
- —
- TTFB
- 2.14 GB
- Power draw
- 287.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.2-3B-Instruct
- Quantization
- Q2_K
- Framework
- llama.cpp
- Version
- v0.49
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 99
- 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)
- 5.57 GB
- OS
- Ubuntu 24.04
- Driver
- 572.83
- CUDA
- 12.8
- Power draw
- 287.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.49 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx
268 tok/s
Decode
1,209.31 tok/s
Prefill
2.46 s
TTFT
5.57 GB
VRAM
—
MTP
287.3 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=2 running model_id=70 at Q2_K