01What it can do
- 2,5B actifs: débit élevé sur GPU grand public
- 262k context for large repositories
- Apache 2.0, usage commercial libre
- Official Ollama tag
- —~23 GB VRAM en Q4: carte 24 GB ou Mac 32 GB conseillé
- —Spécialisé code: moins adapté au chat généraliste
- —No public score in our sources: performance must be verified on your use cases
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 Flint 40B-A2.5B?
To run Flint 40B-A2.5B locally with Q4 quantization, you need about 23 GB of VRAM. An option to compare: GMKtec EVO-X2 64GB / 1TB (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 GMKtec EVO-X2 64GB / 1TB (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.
On the go: Flint 40B-A2.5B also runs on a RTX laptop PC (24 GB of VRAM) →
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.