Llama-3.1-8B-Instruct · FP16
This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (FP16) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
27.91 tok/s
Decode
Decode speed
99.5 tok/s
Prefill
Prefill speed
0.97 s
TTFT
Time to first token
33.18 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · Q4_K_M Decode 53.5 · Prefill 208.91 ·
- llama.cpp · Q5_K_M Decode 46.73 · Prefill 200.62 ·
- llama.cpp · Q8_0 Decode 35.36 · Prefill 182.04 ·
- Ollama · FP16 (current)Decode 27.91 · Prefill 99.5 ·
- Ollama · Q6_K Decode 40.65 · Prefill 194.34 ·
- Ollama · Q8_0 Decode 37 · Prefill 131.55 ·
- llama.cpp · IQ1_S Decode 80.81 · Prefill 288.05 ·
- Ollama · Q4_K_M Decode 51.59 · Prefill 267.45 ·
- Ollama · Q5_K_S Decode 48.77 · Prefill 206.68 ·
Core figures
- Decode (avg)
- 27.91 tok/s
- Prefill (avg)
- 99.5 tok/s
- TTFT (avg)
- 0.97 s
- VRAM (avg)
- 33.18 GB
- MTP acceptance rate
- —
- TTFB
- 0.22 GB
- Power draw
- 69 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Llama-3.1-8B-Instruct
- Quantization
- FP16
- Framework
- Ollama
- Version
- v0.46
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 33.18 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 69 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
Sources & evidence
1 measured records in total, each traceable to its original source
v0.46 · Ubuntu 24.04 · CUDA 13.0 · 32768 ctx
27.91 tok/s
Decode
99.5 tok/s
Prefill
0.97 s
TTFT
33.18 GB
VRAM
—
MTP
69 W
Power draw
L2 batch seed 2026-10-20 (Linux 116GiB unlock): Ollama on Spark running model_id=68 at FP16