Back to search results
Llama-3.1-8B-Instruct · IQ1_S
NVIDIA RTX 509032GBOllama v0.22L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ1_S) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
316.88 tok/s
Decode
Decode speed
1,203.93 tok/s
Prefill
Prefill speed
0.18 s
TTFT
Time to first token
9.16 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ4_XS Decode 310.8 · Prefill 1667.93 ·
- Ollama · IQ1_S (current)Decode 316.88 · Prefill 1203.93 ·
- llama.cpp · Q8_0 Decode 162.5 · Prefill 1218.8 ·
- llama.cpp · Q5_K_M Decode 236.9 · Prefill 1776.8 ·
- llama.cpp · Q4_K_M Decode 285.3 · Prefill 2139.8 ·
Core figures
- Decode (avg)
- 316.88 tok/s
- Prefill (avg)
- 1,203.93 tok/s
- TTFT (avg)
- 0.18 s
- VRAM (avg)
- 9.16 GB
- MTP acceptance rate
- —
- TTFB
- 2.54 GB
- Power draw
- 434.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- IQ1_S
- Framework
- Ollama
- Version
- v0.22
- Context length
- 4096 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 9.16 GB
- OS
- Windows 11 23H2
- Driver
- 570.86
- CUDA
- 12.6
- Power draw
- 434.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.22 · Windows 11 23H2 · CUDA 12.6 · 4096 ctx
316.88 tok/s
Decode
1,203.93 tok/s
Prefill
0.18 s
TTFT
9.16 GB
VRAM
—
MTP
434.3 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=13 running model_id=68 at IQ1_S