Back to search results
Qwen3.5-4B · IQ2_XS
NVIDIA RTX 508016GBllama.cpp v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (IQ2_XS) on NVIDIA RTX 5080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
312.6 tok/s
Decode
Decode speed
1,217.96 tok/s
Prefill
Prefill speed
1.1 s
TTFT
Time to first token
6.13 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ1_S Decode 350.61 · Prefill 1829.73 ·
- llama.cpp · IQ2_XS (current)Decode 312.6 · Prefill 1217.96 ·
- Strata · IQ3_S Decode 356.3 · Prefill 1901.07 ·
- llama.cpp · IQ4_XS Decode 133.14 · Prefill 731.5 ·
- Strata · Q3_K_M Decode 231.73 · Prefill 785.76 ·
Core figures
- Decode (avg)
- 312.6 tok/s
- Prefill (avg)
- 1,217.96 tok/s
- TTFT (avg)
- 1.1 s
- VRAM (avg)
- 6.13 GB
- MTP acceptance rate
- —
- TTFB
- 2.5 GB
- Power draw
- 220.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ2_XS
- Framework
- llama.cpp
- Version
- v0.40
- Context length
- 2048 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 5080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 6.13 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 220.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · Ubuntu 22.04 · CUDA 12.6 · 2048 ctx
312.6 tok/s
Decode
1,217.96 tok/s
Prefill
1.1 s
TTFT
6.13 GB
VRAM
—
MTP
220.1 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=14 running model_id=48 at IQ2_XS