Unlimited-OCR-2
Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.
--vram
--gpus
--quant
--add
On your GPU
- Unlimited-OCR-2
| Property | |
|---|---|
| Overview | |
| Task | OCR |
| Parameters | 3.3B |
| Active parameters | 1.1B |
| Context length | 128K |
| Input → output | |
| Released | 26 Oct 2026 |
| Licence | MIT |
| Gated download | no |
| Memory and speed | |
| Fits your hardwarepick a GPU above | ≈4.5 GB |
| VRAM at Q4 | ≈2.8 GB |
| VRAM at Q8 | ≈4.5 GB |
| VRAM at FP16 | ≈8.0 GB |
| Est. generation speedpick a GPU above | — |
| Popularity | |
| Downloads / 30 days | 604.6K |
| Likes | 714 |
| Runs with | |
| llama.cpp | |
| SGLang | |
| Transformers | |
| vLLM | |
| Ollama tag | — |
| Architecture | |
| Architecture | UnlimitedOCRForCausalLM |
| Layers | 12 |
| Attention / KV heads | 10 / 10 |
| Vocabulary | 129 280 |
| Weights dtype | bfloat16 |
| GGUF available | yes |
Keep comparing
Memory figures are estimates for an 8K context at the chosen quantisation (Q4_K_M for LLMs by default). Speeds are rough, memory-bound estimates. Self-reported benchmark scores come from the model authors.