Back to search results
Qwen3.5-0.8B · Q4_K_S
NVIDIA RTX 508016GBllama.cpp v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q4_K_S) on NVIDIA RTX 5080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
332.25 tok/s
Decode
Decode speed
1,390.04 tok/s
Prefill
Prefill speed
2.04 s
TTFT
Time to first token
3.41 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ3_XS Decode 314.6 · Prefill 1036.31 ·
- llama.cpp · Q4_K_S (current)Decode 332.25 · Prefill 1390.04 ·
- Strata · IQ2_M Decode 312.53 · Prefill 1045.98 ·
- Strata · IQ3_XS Decode 375.51 · Prefill 1862.92 ·
- llama.cpp · IQ2_M Decode 338.41 · Prefill 1613.66 ·
- Strata · FP16 Decode 178.36 · Prefill 737.11 ·
- Strata · Q4_K_S Decode 363.26 · Prefill 1495.67 ·
Core figures
- Decode (avg)
- 332.25 tok/s
- Prefill (avg)
- 1,390.04 tok/s
- TTFT (avg)
- 2.04 s
- VRAM (avg)
- 3.41 GB
- MTP acceptance rate
- —
- TTFB
- 2.66 GB
- Power draw
- 263.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q4_K_S
- Framework
- llama.cpp
- Version
- v0.21
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 99
- Flash Attention
- Off
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)
- 3.41 GB
- OS
- Ubuntu 24.04
- Driver
- 572.83
- CUDA
- 12.8
- Power draw
- 263.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx
332.25 tok/s
Decode
1,390.04 tok/s
Prefill
2.04 s
TTFT
3.41 GB
VRAM
—
MTP
263.7 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=14 running model_id=51 at Q4_K_S