Back to search results
Qwen3.5-0.8B · FP16
NVIDIA RTX 5070 Ti16GBvLLM v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (FP16) on NVIDIA RTX 5070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
121.99 tok/s
Decode
Decode speed
561.36 tok/s
Prefill
Prefill speed
1.5 s
TTFT
Time to first token
5.21 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · FP16 (current)Decode 121.99 · Prefill 561.36 ·
- vLLM · Q6_K Decode 174.9 · Prefill 685.31 ·
- Strata · Q5_K_M Decode 251.18 · Prefill 1222.13 ·
- Strata · Q6_K Decode 237.15 · Prefill 1031.12 ·
Core figures
- Decode (avg)
- 121.99 tok/s
- Prefill (avg)
- 561.36 tok/s
- TTFT (avg)
- 1.5 s
- VRAM (avg)
- 5.21 GB
- MTP acceptance rate
- —
- TTFB
- 0.98 GB
- Power draw
- 267.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- FP16
- Framework
- vLLM
- Version
- v0.23
- Context length
- 16384 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5070 Ti
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 5.21 GB
- OS
- Ubuntu 22.04
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 267.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · Ubuntu 22.04 · CUDA 12.8 · 16384 ctx
121.99 tok/s
Decode
561.36 tok/s
Prefill
1.5 s
TTFT
5.21 GB
VRAM
—
MTP
267.4 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=17 running model_id=51 at FP16