QW

Andy 3.5 beta

QwenGGUF by SweaterdogUpdated 2025-02-06
Download on Hugging Face
Parameters7.62B
Context128K
Layers28
Architectureqwen2
Smallest quant15.2 GB
Quick answer

Andy 3.5 beta needs about 16.2 GB of memory at F16 (a 15.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Andy 3.5 beta – a Qwen2.5‑7B finetuned for Minecraft and instruction following

Andy 3.5 beta is a finetuned Qwen2.5‑7B model released by Sweaterdog. It is built on unsloth/Qwen2.5‑7B‑bnb‑4bit and targets Minecraft gameplay and general instruction following. The model is available in a single F16 GGUF file.

Good at

  • Minecraft gameplay
  • Instruction following
  • Long‑context generation up to 131,072 tokens

Limits

  • No vision support
  • Requires 16.2 GB VRAM for 8 k context
  • License is apache‑2.0

Best for

  • Gaming bots
  • Chatbots needing long context
  • Educational coding assistants

Who it’s for. Developers and hobbyists who want a lightweight Minecraft‑focused LLM. The model is a beta and not final, but useful for testing new training methods.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1615.2 GB 16.2 GB
Too big Get file →

The only available quant is F16, 15.24 GB on disk and about 16.2 GB VRAM at 8 k context. For 16 GB or larger VRAM, F16 is recommended. No other quants are provided.

What GPU do you need for Andy 3.5 beta?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is F16 (15.2 GB file, about 16.2 GB in use).

Which Andy 3.5 beta quant should you choose?

F16 (15.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters7.62B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized bySweaterdog
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,215
Last updated2025-02-06

Frequently asked questions about Andy 3.5 beta

How much VRAM does Andy 3.5 beta need?

About 16.2 GB at F16 with an 8K context window. That is the 15.2 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 Andy 3.5 beta on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Andy 3.5 beta GGUF?

It depends on the quant: F16 is 15.2 GB.

What context length does Andy 3.5 beta support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Andy 3.5 beta GGUF?

The files are on Hugging Face in the Sweaterdog/Andy-3.5-beta repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Andy 3.5 beta 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 Andy 3.5 beta on 8 GB VRAM?

No, the F16 quant requires about 16.2 GB VRAM at 8 k context, so 8 GB VRAM is insufficient.

Does Andy 3.5 beta support vision?

No, the model does not include vision capabilities.

Other GGUFs of Qwen2.5-7B-bnb-4bit

Similar models

Browse all →

More from Sweaterdog

All by Sweaterdog →

More Qwen models

All Qwen →

Other small models

All small models →