Back to search results
Llama-3.1-8B-Instruct · IQ2_XS
NVIDIA RTX 4080 Super16GBStrata v0.32L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ2_XS) on NVIDIA RTX 4080 Super with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
307.75 tok/s
Decode
Decode speed
1,104.97 tok/s
Prefill
Prefill speed
2.04 s
TTFT
Time to first token
10.16 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · Q3_K_M Decode 201.4 · Prefill 1061.69 ·
- Strata · IQ2_XS (current)Decode 307.75 · Prefill 1104.97 ·
- Strata · Q5_K_M Decode 179.72 · Prefill 584.63 ·
- vLLM · IQ2_M Decode 224.52 · Prefill 1147.46 ·
- vLLM · Q3_K_L Decode 177.01 · Prefill 908.47 ·
- Ollama · IQ2_M Decode 204.79 · Prefill 1109.54 ·
Core figures
- Decode (avg)
- 307.75 tok/s
- Prefill (avg)
- 1,104.97 tok/s
- TTFT (avg)
- 2.04 s
- VRAM (avg)
- 10.16 GB
- MTP acceptance rate
- 0.65
- TTFB
- 2.46 GB
- Power draw
- 296.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- IQ2_XS
- Framework
- Strata
- Version
- v0.32
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 5
- 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 Super
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 10.16 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.4
- Power draw
- 296.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.32 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx
307.75 tok/s
Decode
1,104.97 tok/s
Prefill
2.04 s
TTFT
10.16 GB
VRAM
0.65
MTP
296.8 W
Power draw
L2 batch seed 2026-10-19: Strata on hw_id=20 running model_id=68 at IQ2_XS