01What it can do
- Apache 2.0 (free for commercial use)
- 20B dense, code-focused
- 128k native context
- Clear code specialization
- —Gated on Hugging Face (click-through)
- —No official Ollama tag — install via HuggingFace
- —Mixed precision: runtime compatibility must be verified
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 Granite Code 20B (Mixed Precision)?
To run Granite Code 20B (Mixed Precision) locally with Q4 quantization, you need about 12 GB of VRAM. An option to compare: RTX 5070 12GB (ASUS Prime OC) — leave some headroom for the system and context; check engine compatibility with the GPU.
Affiliate links — commission possible at no extra cost to you; independent recommendations. As an Amazon Associate, BestLLMfor earns from qualifying purchases.
On the go: Granite Code 20B (Mixed Precision) also runs on a RTX laptop PC (16 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.