LO

Loom Weave 4

LoomGGUF by textilelabsUpdated 2026-10-06
Download on Hugging Face
Parameters56M
Context32K
Layers24
Architecturegemma3
Smallest quant0.0 GB
Quick answer

Loom Weave 4 needs about 0.6 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.0 GB (Q4_K_M) to 0.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.2 GB.

Loom Weave 4 – 55.6M‑parameter Gemma3 model with 8K context

Loom Weave 4 is a 55.6M‑parameter Gemma3 model trained from scratch. It supports 8K context and is optimized for phone and desktop chat applications. The model is released under the MIT license.

Good at

  • Tools usage
  • Short‑form chat
  • Phone‑friendly inference

Limits

  • No vision support
  • Limited to 8K context
  • Requires GGUF format

Best for

  • Mobile chat bots
  • Lightweight desktop assistants
  • Educational demos

Who it’s for. Developers building lightweight conversational agents who need a small, phone‑ready model. The model is ideal for projects that require tool‑integrated reasoning without large GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.0 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.1 GB 0.7 GB
Fits Get file →

For 8GB VRAM, the Q4_K_M quant (0.04 GB file, ~0.6 GB memory at 8K context) is recommended. If more memory is available, Q8_0 (0.06 GB file, ~0.6 GB memory) offers higher precision. The F16 quant (0.11 GB file, ~0.7 GB memory) provides full‑precision inference but needs more VRAM.

What GPU do you need for Loom Weave 4?

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 F16 (0.1 GB file, about 0.7 GB in use).

Which Loom Weave 4 quant should you choose?

Q4_K_M is the usual starting point for Loom Weave 4: it balances file size and quality well. Here it is a 0.0 GB file.

The Q8_0 file is 0.1 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters56M
Layers24
Trained context32,768 tokens
KV cache (fp16)6 KB per token

Source

Quantized bytextilelabs
FamilyLoom
Licensemit
Downloads (HF)602
Last updated2026-10-06

Frequently asked questions about Loom Weave 4

How much VRAM does Loom Weave 4 need?

About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.0 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 Loom Weave 4 on an 8 GB GPU?

Yes, with F16: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Loom Weave 4 GGUF?

It depends on the quant: Q4_K_M is 0.0 GB, Q8_0 is 0.1 GB, F16 is 0.1 GB.

What context length does Loom Weave 4 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.2 GB at 32K.

Where can I download Loom Weave 4 GGUF?

The files are on Hugging Face in the textilelabs/Loom-Weave-4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Loom Weave 4 use?

Hugging Face lists the license as mit. 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 Loom Weave 4 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 0.6 GB of VRAM at 8K context, fitting comfortably in 8 GB.

Does Loom Weave 4 support vision tasks?

No, the model does not include vision capabilities.

Similar models

Browse all →

More from textilelabs

All by textilelabs →

More Loom models

All Loom →

Other tiny models

All tiny models →