01What it can do
- 75B/9B active MoE: lighter inference than an equivalent dense model
- Reasoning-focused
- 128k native context
- Commercial use permitted (NVIDIA Open Model License)
- —150 GB in FP16 — reserved for high-end configurations
- —~44 GB VRAM even in Q4 (2× RTX 4090 or Mac 64 GB+)
- —No official Ollama tag—install via HuggingFace/vLLM
04Install
Install Ollama for your OS. Check the model and its quantization before downloading. Start with 4096 tokens of context, then check placement with ollama ps. A command below is not proof that a test was run on your machine.
02Required memory
Approximate GPU VRAM required to run this model, including 4k tokens of context overhead. For a longer context, add ~1 GB per 8k-token increment.
What hardware do you need for Nemotron 3 Puzzle 75B-A9B?
To run Nemotron 3 Puzzle 75B-A9B locally with Q4 quantization, you need about 44 GB of VRAM. An option to compare: BOSGAME M5 128GB / 2TB (Ryzen AI Max+ 395) — leave some headroom for the system and context; check engine compatibility with the GPU.
Why this choice? Our complete guide on BOSGAME M5 128GB / 2TB (Ryzen AI Max+ 395) →
Affiliate links — commission possible at no extra cost to you; independent recommendation. As an Amazon Associate, BestLLMfor earns from qualifying purchases.
03Expected speed
Tokens generated per second in Q4_K_M, 4k context. Beyond 20 t/s, reading is comfortable. Below 10 t/s, that's just for testing.