Back to search results
Qwen3.5-4B · Q3_K_M
NVIDIA RTX 508016GBStrata v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_M) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
231.73 tok/s
Decode
Decode speed
785.76 tok/s
Prefill
Prefill speed
1.65 s
TTFT
Time to first token
7.81 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ4_XS Decode 133.14 · Prefill 731.5 ·
- Strata · Q3_K_M (current)Decode 231.73 · Prefill 785.76 ·
Core figures
- Decode (avg)
- 231.73 tok/s
- Prefill (avg)
- 785.76 tok/s
- TTFT (avg)
- 1.65 s
- VRAM (avg)
- 7.81 GB
- MTP acceptance rate
- 0.51
- TTFB
- 1.85 GB
- Power draw
- 268 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q3_K_M
- Framework
- Strata
- Version
- v0.37
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 15
- 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)
- 7.81 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 268 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx
231.73 tok/s
Decode
785.76 tok/s
Prefill
1.65 s
TTFT
7.81 GB
VRAM
0.51
MTP
268 W
Power draw
L2 batch seed 2026-10-10: Strata on hw_id=14 running model_id=48 at Q3_K_M