Back to search results
Llama-3.2-3B-Instruct · Q5_K_S
NVIDIA RTX 408016GBllama.cpp v0.27L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q5_K_S) on NVIDIA RTX 4080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
338.44 tok/s
Decode
Decode speed
1,522.16 tok/s
Prefill
Prefill speed
2.49 s
TTFT
Time to first token
7.77 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q3_K_S Decode 351.55 · Prefill 1651.53 ·
- llama.cpp · Q5_K_S (current)Decode 338.44 · Prefill 1522.16 ·
- Strata · Q4_K_M Decode 341.28 · Prefill 1116.7 ·
Core figures
- Decode (avg)
- 338.44 tok/s
- Prefill (avg)
- 1,522.16 tok/s
- TTFT (avg)
- 2.49 s
- VRAM (avg)
- 7.77 GB
- MTP acceptance rate
- —
- TTFB
- 2.71 GB
- Power draw
- 238.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.2-3B-Instruct
- Quantization
- Q5_K_S
- Framework
- llama.cpp
- Version
- v0.27
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 33
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 7.77 GB
- OS
- Ubuntu 22.04
- Driver
- 572.83
- CUDA
- 12.6
- Power draw
- 238.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · Ubuntu 22.04 · CUDA 12.6 · 32768 ctx
338.44 tok/s
Decode
1,522.16 tok/s
Prefill
2.49 s
TTFT
7.77 GB
VRAM
—
MTP
238.5 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=41 running model_id=70 at Q5_K_S