1× RTX PRO 6000
281tok/sPeak
1 request, synthetic prompt Source
Intelligenceno independent value
Local AI · Recipe · 1× RTX 5090
Llama 7B Q4_0 with llama.cpp on 1× RTX 5090
Llama 7B Q4_0 with llama.cpp on 1× RTX 5090: 300 tok/s according to github.com (dataset as of Nov 3, 2026).
by ggml-org
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- llama.cpp commit lt. Scoreboard
- Quantization
- GGUF Q4_0
- Model family
- Llama
- Context
- —
- Parameters
- 7B dense
- Creator
- ggml-org
- GitHub stars
- 133,144
- Repo updated
- Nov 2, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Decode · 1 request
Prefill by context
What you need
- Hardware
- 1 × NVIDIA RTX 5090
- Weights
- Main weightsTheBloke/Llama-2-7B-GGUF llama2
- Engine
- llama.cpp commit lt. Scoreboard
Related recipes
1× RTX 3090
162tok/sPeak
1 request, synthetic prompt Source
Intelligenceno independent value
1× RTX 5090
no documented speed
Intelligence7no thinking
- Access on request
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.