Back to search results
Qwen3.5-0.8B · IQ3_XS
NVIDIA RTX 308010GBllama.cpp v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_XS) on NVIDIA RTX 3080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
222.89 tok/s
Decode
Decode speed
1,012.61 tok/s
Prefill
Prefill speed
0.16 s
TTFT
Time to first token
3.14 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 Decode 193.95 · Prefill 916.23 ·
- llama.cpp · IQ3_XS (current)Decode 222.89 · Prefill 1012.61 ·
Core figures
- Decode (avg)
- 222.89 tok/s
- Prefill (avg)
- 1,012.61 tok/s
- TTFT (avg)
- 0.16 s
- VRAM (avg)
- 3.14 GB
- MTP acceptance rate
- —
- TTFB
- 1.78 GB
- Power draw
- 298.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ3_XS
- Framework
- llama.cpp
- Version
- v0.40
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 28
- 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)
- 3.14 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 298.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · Ubuntu 24.04 · CUDA 12.4 · 8192 ctx
222.89 tok/s
Decode
1,012.61 tok/s
Prefill
0.16 s
TTFT
3.14 GB
VRAM
—
MTP
298.1 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=44 running model_id=51 at IQ3_XS