Qwen3.5-0.8B · IQ1_S
This page aggregates 2 real-world runs of Qwen3.5-0.8B (IQ1_S) on NVIDIA RTX 4080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
334.33 tok/s
Decode
Decode speed
1,448.23 tok/s
Prefill
Prefill speed
1.52 s
TTFT
Time to first token
2.8 GB
VRAM
VRAM usage
2
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q3_K_S Decode 378.63 · Prefill 1756.55 ·
- vLLM · Q5_K_M Decode 304.13 · Prefill 1485.96 ·
- Strata · IQ1_S (current)Decode 334.33 · Prefill 1448.23 ·
- Strata · Q8_0 Decode 328.32 · Prefill 1297.3 ·
- vLLM · Q6_K Decode 169.83 · Prefill 688.66 ·
- Strata · Q3_K_S Decode 370.12 · Prefill 1878.16 ·
Core figures
- Decode (avg)
- 334.33 tok/s
- Prefill (avg)
- 1,448.23 tok/s
- TTFT (avg)
- 1.52 s
- VRAM (avg)
- 2.8 GB
- MTP acceptance rate
- 0.67
- TTFB
- 2.67 GB
- Power draw
- 277.45 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ1_S
- Framework
- Strata
- Version
- v0.27
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 8
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 2.8 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 277.9 W
Sources & evidence
2 measured records in total, each traceable to its original source
v0.27 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx
343.08 tok/s
Decode
1,201.46 tok/s
Prefill
1.53 s
TTFT
2.8 GB
VRAM
0.58
MTP
277.9 W
Power draw
L2 batch seed 2026-10-18: Strata on hw_id=41 running model_id=51 at IQ1_S
v0.53 · Ubuntu 22.04 · CUDA 12.6 · 8192 ctx
325.58 tok/s
Decode
1,695 tok/s
Prefill
1.52 s
TTFT
2.8 GB
VRAM
0.76
MTP
277 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=41 running model_id=51 at IQ1_S