Back to search results
Llama-3.1-8B-Instruct · IQ2_XS
NVIDIA RTX 409024GBvLLM v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ2_XS) on NVIDIA RTX 4090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
205.12 tok/s
Decode
Decode speed
1,126.08 tok/s
Prefill
Prefill speed
1.81 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
17 days ago
Last verified
Performance
- vLLM · IQ2_XS (current)Decode 205.12 · Prefill 1126.08 ·
- Strata · Q4_K_M Decode 191.74 · Prefill 642.2 ·
- Strata · Q6_K Decode 151.86 · Prefill 574.29 ·
- llama.cpp · Q5_K_M Decode 128.55 · Prefill 827.45 ·
- vLLM · Q4_K_M Decode 142.74 · Prefill 510.45 ·
- llama.cpp · Q8_0 Decode 91.4 · Prefill 685.5 ·
- llama.cpp · Q4_K_M Decode 160.5 · Prefill 1203.8 ·
Core figures
- Decode (avg)
- 205.12 tok/s
- Prefill (avg)
- 1,126.08 tok/s
- TTFT (avg)
- 1.81 s
- VRAM (avg)
- 10.16 GB
- MTP acceptance rate
- —
- TTFB
- 1.64 GB
- Power draw
- 394.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.31
- Context length
- 4096 tokens
- Batch size
- 8
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 10.16 GB
- OS
- Windows 11 24H2
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 394.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · Windows 11 24H2 · CUDA 12.4 · 4096 ctx
205.12 tok/s
Decode
1,126.08 tok/s
Prefill
1.81 s
TTFT
10.16 GB
VRAM
—
MTP
394.6 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=1 running model_id=68 at IQ2_XS