QW

Connectailab CHOCO BRAIN v1 Merged

QwenGGUF by hwihwalabUpdated 2026-10-31
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.8 GB
Quick answer

Connectailab CHOCO BRAIN v1 Merged needs about 1.7 GB of memory at its main file (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Connectailab CHOCO BRAIN v1 Merged – a 0.8B parameter decision engine for indie game studios

Connectailab CHOCO BRAIN v1 Merged is a 0.8B parameter model built on Qwen3.5-0.8B. It is a causal language model with a vision encoder, trained for structured decision making in game studio workflows. The model outputs JSON action keys rather than conversational text.

Good at

  • Structured decision making
  • Zero‑latency action verdicts
  • Game studio workflow automation

Limits

  • Not a general chatbot
  • No vision support beyond pre‑training
  • Requires 1.7GB VRAM at 8k context

Best for

  • Steam live‑ops triage
  • Crash and refund audit automation
  • Multi‑agent swarm orchestration

Who it’s for. Developers and operations teams in independent game studios who need an on‑device executive cortex for rapid, structured decision making. The model is tailored to Steam live‑ops, crash triage, refund audits, and publishing contract analysis.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.8 GB 1.7 GB
Fits Get file →

The only available quant is unknown. The .gguf file is 0.81GB and requires approximately 1.7GB VRAM at 8k context. For 8GB VRAM you can run this quant directly. If you need lower memory, no other quant is available in the file list.

What GPU do you need for Connectailab CHOCO BRAIN v1 Merged?

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 the main file (0.8 GB file, about 1.7 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byhwihwalab
FamilyQwen
Licenseapache-2.0
Downloads (HF)928
Last updated2026-10-31

Frequently asked questions about Connectailab CHOCO BRAIN v1 Merged

How much VRAM does Connectailab CHOCO BRAIN v1 Merged need?

About 1.7 GB at its main file with an 8K context window. That is the 0.8 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 Connectailab CHOCO BRAIN v1 Merged on an 8 GB GPU?

Yes, with the smaller files: the 0.8 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Connectailab CHOCO BRAIN v1 Merged GGUF?

It depends on the quant: file is 0.8 GB.

What context length does Connectailab CHOCO BRAIN v1 Merged support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Connectailab CHOCO BRAIN v1 Merged GGUF?

The files are on Hugging Face in the hwihwalab/connectailab-CHOCO-BRAIN-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Connectailab CHOCO BRAIN v1 Merged 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 model requires about 1.7GB VRAM at 8k context, so 8GB is sufficient.

Does this model support vision tasks?

No, it is a language model with a vision encoder but is not intended for vision inference.

What license applies to this model?

The model is released under apache-2.0.

Other GGUFs of Qwen3.5-0.8B

Similar models

Browse all →

More from hwihwalab

All by hwihwalab →

More Qwen models

All Qwen →

Other tiny models

All tiny models →