Back to search results
Llama-3-8B-Instruct · Q3_K_M
NVIDIA RTX 309024GBStrata v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q3_K_M) on NVIDIA RTX 3090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
136.06 tok/s
Decode
Decode speed
696.33 tok/s
Prefill
Prefill speed
2.37 s
TTFT
Time to first token
13.52 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Ollama · IQ3_S Decode 90.89 · Prefill 298.18 ·
- Ollama · Q4_K_M Decode 84.07 · Prefill 419.77 ·
- Strata · IQ4_XS Decode 126.45 · Prefill 522.82 ·
- Strata · Q3_K_M (current)Decode 136.06 · Prefill 696.33 ·
- llama.cpp · Q8_0 Decode 84.9 · Prefill 636.8 ·
- llama.cpp · Q5_K_M Decode 123.7 · Prefill 927.8 ·
- llama.cpp · Q4_K_M Decode 149 · Prefill 1117.5 ·
Core figures
- Decode (avg)
- 136.06 tok/s
- Prefill (avg)
- 696.33 tok/s
- TTFT (avg)
- 2.37 s
- VRAM (avg)
- 13.52 GB
- MTP acceptance rate
- 0.6
- TTFB
- 1.09 GB
- Power draw
- 294.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3-8B-Instruct
- Quantization
- Q3_K_M
- Framework
- Strata
- Version
- v0.21
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 15
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 13.52 GB
- OS
- Ubuntu 22.04
- Driver
- 570.86
- CUDA
- 13.0
- Power draw
- 294.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · Ubuntu 22.04 · CUDA 13.0 · 2048 ctx
136.06 tok/s
Decode
696.33 tok/s
Prefill
2.37 s
TTFT
13.52 GB
VRAM
0.6
MTP
294.4 W
Power draw
L2 batch seed 2026-10-18: Strata on hw_id=2 running model_id=69 at Q3_K_M