Back to search results
Llama-3.1-8B-Instruct · IQ3_XS
NVIDIA RTX 309024GBOllama v0.29L2 Cross-framework verified
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ3_XS) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
101.05 tok/s
Decode
Decode speed
370.05 tok/s
Prefill
Prefill speed
1.79 s
TTFT
Time to first token
12.52 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- vLLM · Q8_0 Decode 64.44 · Prefill 290.44 ·
- Ollama · IQ3_XS (current)Decode 101.05 · Prefill 370.05 ·
- llama.cpp · IQ3_XS Decode 111.47 · Prefill 506.1 ·
- llama.cpp · Q4_K_M Decode 116.04 · Prefill 765.01 ·
- Ollama · IQ2_XS Decode 106.45 · Prefill 486.76 ·
- llama.cpp · Q8_0 Decode 84.9 · Prefill 636.8 ·
- llama.cpp · Q5_K_M Decode 123.7 · Prefill 927.8 ·
Core figures
- Decode (avg)
- 101.05 tok/s
- Prefill (avg)
- 370.05 tok/s
- TTFT (avg)
- 1.79 s
- VRAM (avg)
- 12.52 GB
- MTP acceptance rate
- —
- TTFB
- 0.81 GB
- Power draw
- 258.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- IQ3_XS
- Framework
- Ollama
- Version
- v0.29
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 33
- 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)
- 12.52 GB
- OS
- Windows 11 23H2
- Driver
- 572.83
- CUDA
- 12.6
- Power draw
- 258.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.29 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx
101.05 tok/s
Decode
370.05 tok/s
Prefill
1.79 s
TTFT
12.52 GB
VRAM
—
MTP
258.1 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=2 running model_id=68 at IQ3_XS