Back to search results
Llama-3.1-8B-Instruct · Q6_K
NVIDIA RTX 409024GBStrata v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q6_K) on NVIDIA RTX 4090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
151.86 tok/s
Decode
Decode speed
574.29 tok/s
Prefill
Prefill speed
2.15 s
TTFT
Time to first token
18.9 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 Decode 205.12 · Prefill 1126.08 ·
- Strata · Q4_K_M Decode 191.74 · Prefill 642.2 ·
- Strata · Q6_K (current)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)
- 151.86 tok/s
- Prefill (avg)
- 574.29 tok/s
- TTFT (avg)
- 2.15 s
- VRAM (avg)
- 18.9 GB
- MTP acceptance rate
- 0.77
- TTFB
- 1.21 GB
- Power draw
- 370.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- Q6_K
- Framework
- Strata
- Version
- v0.37
- Context length
- 2048 tokens
- Batch size
- 256
- 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 4090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 18.9 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 370.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx
151.86 tok/s
Decode
574.29 tok/s
Prefill
2.15 s
TTFT
18.9 GB
VRAM
0.77
MTP
370.3 W
Power draw
L2 batch seed 2026-10-19: Strata on hw_id=1 running model_id=68 at Q6_K