Back to search results
Qwen3.5-0.8B · IQ2_M
NVIDIA RTX 508016GBStrata v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_M) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
312.53 tok/s
Decode
Decode speed
1,045.98 tok/s
Prefill
Prefill speed
1.98 s
TTFT
Time to first token
2.97 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 Decode 332.25 · Prefill 1390.04 ·
- Strata · IQ2_M (current)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)
- 312.53 tok/s
- Prefill (avg)
- 1,045.98 tok/s
- TTFT (avg)
- 1.98 s
- VRAM (avg)
- 2.97 GB
- MTP acceptance rate
- 0.67
- TTFB
- 2.5 GB
- Power draw
- 208.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ2_M
- Framework
- Strata
- Version
- v0.37
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 12
- 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)
- 2.97 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- 13.0
- Power draw
- 208.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Windows 11 23H2 · CUDA 13.0 · 2048 ctx
312.53 tok/s
Decode
1,045.98 tok/s
Prefill
1.98 s
TTFT
2.97 GB
VRAM
0.67
MTP
208.3 W
Power draw
L2 batch seed 2026-10-18: Strata on hw_id=14 running model_id=51 at IQ2_M