OR

Orb Human Typeahead 1b v2.3

OrbGGUF by chartreuse-verteUpdated 2026-10-31
Download on Hugging Face
Parameters1.63B
Context128K
Layers40
Architecturegranite
Smallest quant1.0 GB
Quick answer

Orb Human Typeahead 1b v2.3 needs about 2.1 GB of memory at Q4_0 (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.0 GB (Q4_0) to 1.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Ghost‑text autocomplete for roleplay chat

Orb Human Typeahead 1b v2.3 predicts the next few words a user will type in a roleplay conversation. It is fine‑tuned on partial user messages and context to keep suggestions on‑scene and in‑voice. The model is available in Q4_0 and Q8_0 quantizations.

Good at

  • Roleplay text completion
  • Maintains character voice
  • Triggers only at word boundaries

Limits

  • No vision support
  • Requires up to 131072 context tokens
  • Apache‑2.0 license

Best for

  • Typing assistants for roleplay games
  • Chatbot UI autocompletion
  • Interactive storytelling tools

Who it’s for. Developers building roleplay chat interfaces or interactive fiction tools. The model is suitable for applications that need real‑time ghost‑text suggestions without generating full replies.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.0 GB 2.1 GB
Fits Get file →
Q8_01.7 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, use the Q4_0 quant (0.97 GB file, ~2.1 GB VRAM at 8 k context). For 16 GB VRAM, Q8_0 (1.74 GB file, ~2.9 GB VRAM at 8 k context) offers higher precision. Memory estimates are approximate.

What GPU do you need for Orb Human Typeahead 1b v2.3?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q8_0 (1.7 GB file, about 2.9 GB in use).

Which Orb Human Typeahead 1b v2.3 quant should you choose?

Q4_0 (1.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters1.63B
Layers40
Trained context131,072 tokens
KV cache (fp16)80 KB per token

Source

Quantized bychartreuse-verte
FamilyOrb
Licenseapache-2.0
Downloads (HF)769
Last updated2026-10-31

Frequently asked questions about Orb Human Typeahead 1b v2.3

How much VRAM does Orb Human Typeahead 1b v2.3 need?

About 2.1 GB at Q4_0 with an 8K context window. That is the 1.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Orb Human Typeahead 1b v2.3 on an 8 GB GPU?

Yes, with Q8_0: the 1.7 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Orb Human Typeahead 1b v2.3 GGUF?

It depends on the quant: Q4_0 is 1.0 GB, Q8_0 is 1.7 GB.

What context length does Orb Human Typeahead 1b v2.3 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Orb Human Typeahead 1b v2.3 GGUF?

The files are on Hugging Face in the chartreuse-verte/orb-human-typeahead-1b-v2.3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Orb Human Typeahead 1b v2.3 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q4_0 quant uses about 2.1 GB VRAM at 8 k context, fitting within an 8 GB GPU.

Does the model support image inputs?

No, the model only processes plain text and has no vision capability.

What license does the model use?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from chartreuse-verte

All by chartreuse-verte →

Other tiny models

All tiny models →