Back to search results
Qwen3.5-0.8B · IQ3_S
NVIDIA RTX 308010GBllama.cpp v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_S) on NVIDIA RTX 3080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
193.95 tok/s
Decode
Decode speed
916.23 tok/s
Prefill
Prefill speed
2.09 s
TTFT
Time to first token
3.21 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ3_S (current)Decode 193.95 · Prefill 916.23 ·
- llama.cpp · IQ3_XS Decode 222.89 · Prefill 1012.61 ·
Core figures
- Decode (avg)
- 193.95 tok/s
- Prefill (avg)
- 916.23 tok/s
- TTFT (avg)
- 2.09 s
- VRAM (avg)
- 3.21 GB
- MTP acceptance rate
- —
- TTFB
- 1.55 GB
- Power draw
- 363.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ3_S
- Framework
- llama.cpp
- Version
- v0.23
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 33
- 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)
- 3.21 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 363.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · Ubuntu 22.04 · CUDA 12.6 · 4096 ctx
193.95 tok/s
Decode
916.23 tok/s
Prefill
2.09 s
TTFT
3.21 GB
VRAM
—
MTP
363.8 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=44 running model_id=51 at IQ3_S