1× RTX 5090
300tok/sPeak
1 request, synthetic prompt Source
Intelligenceno independent value
Local AI · Recipe · 1× RTX 5090
Llama 8B FP16 with vLLM on 1× RTX 5090
by DaytonLecoq
No speed value is documented for this recipe, so this page is not indexed.
Engine
- Engine
- vLLM nightly
- Quantization
- FP16
- Model family
- Llama
- Context
- —
- Parameters
- 8B dense
- Creator
- DaytonLecoq
- GitHub stars
- 0
- Repo updated
- May 11, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
No sourced measurements for this recipe.
What you need
- Hardware
- 1 × NVIDIA RTX 5090
- Weights
- Main weightsmeta-llama/Llama-3.1-8B-Instruct llama3.1Access on request
- Engine
- vLLM nightly
Notes
What matters before you rebuild it.
- Smoke test
- Access on request
Sources
Related recipes
1× RTX PRO 6000
281tok/sPeak
1 request, synthetic prompt Source
Intelligenceno independent value
1× RTX 3090
162tok/sPeak
1 request, synthetic prompt Source
Intelligenceno independent value
1× RTX 5090
252tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
1× RTX 5090
128tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
1× RTX 5090
186tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence21with thinkingno thinking 20
- Custom kernel required
Local AI in your company?
In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.