01What it can do
- Full multimodal: image, audio, and text
- Massive context up to 1M tokens
- MoE: only 41B active out of 975B
- Permissive Apache 2.0 license
- —Extremely heavy: ~566 GB of VRAM in Q4, reserved for multi-GPU servers
- —Low local throughput (~5 tok/s in Q4)
- —No Ollama tag — install via HuggingFace
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 Inkling?
To run Inkling locally with Q4 quantization, you need about 566 GB of VRAM. An option to compare: BOSGAME M5 128GB / 2TB (Ryzen AI Max+ 395) — this model exceeds this mini-PC's GPU capacity: choose a smaller model or suitable infrastructure.
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 recommendations. As an Amazon Associate, BestLLMfor earns from qualifying purchases.
Too large for your machine? The kit gives you the model that fits in your VRAM
- Lifetime online access
- PDF + files
- Lifetime updates
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.