2× RTX 3090
179tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligence18with thinkingno thinking 15
- License unclear
Local AI · Recipe · 2× RTX 3090
Nex-N2.5-mini 35B INT4/INT8 with vLLM on 2× RTX 3090
by tonyd2wild
187tok/sEveryday
1 request, prose prompt, prompt 450 tokens, no speculative decoding
Source: github.comIntelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- vLLM 0.27.1
- Quantization
- Int4-Int8Mix + FP8 e5m2 KV
- Model family
- Nex-N2.5-mini
- Context
- 262,144
- Parameters
- 35B-A3B
- Creator
- tonyd2wild
- GitHub stars
- 0
- Repo updated
- Sep 9, 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
- 2 × NVIDIA RTX 3090
- Weights
- Main weightsTech2wild/Nex-N2.5-mini-Int4-Int8Mix Apache-2.0
- Basenex-agi/Nex-N2.5-mini Apache-2.0
- Engine
- vLLM 0.27.1
- Context
- 262,144 tokens
Related recipes
2× RTX 3090
151tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
2× RTX 3090
144tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
2× RTX 3090
123tok/sEveryday
1 request, prose prompt, with Draft Source
Intelligence34with thinkingno thinking 20
2× RTX 3090
109tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence21with thinkingno thinking 20
2× RTX 3090Qwen3.8-27B (ThinkingCap-Finetune)
108tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligenceno independent value
- Experimental
- Custom kernel required
- License unclear
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.