Loom Spark 3.2 needs about 0.6 GB of memory at F16 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Loom Spark 3.2 – 22.8 M parameter LLaMA model with 2,048 token context
Loom Spark 3.2 is a 22.8 M parameter LLaMA model trained from scratch. It supports tool use and has a 2,048 token context window. The model is released under the MIT license.
Good at
- Tool use
- Longer context handling
- Fact‑aware decline generation
Limits
- No vision support
- No other languages listed
- Small parameter size limits complex reasoning
Best for
- Chatbots needing quick fact checks
- Lightweight inference on edge devices
- Tool‑integrated assistants
Who it’s for. Developers building lightweight LLM applications that require tool integration and reliable fact handling. The model is ideal for projects with limited GPU memory and a need for a permissive MIT license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.0 GB | 0.6 GB | Fits | Get file → |
The only available quant is F16, 0.05 GB file size with an estimated 0.6 GB VRAM usage at 8k context. This is suitable for systems with 4 GB or more VRAM. No other quantizations are provided.
What GPU do you need for Loom Spark 3.2?
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 (0.0 GB file, about 0.6 GB in use).
Which Loom Spark 3.2 quant should you choose?
F16 (0.0 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
Source
Frequently asked questions about Loom Spark 3.2
How much VRAM does Loom Spark 3.2 need?
About 0.6 GB at F16 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 Spark 3.2 on an 8 GB GPU?
Yes, with F16: the 0.0 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Loom Spark 3.2 GGUF?
It depends on the quant: F16 is 0.0 GB.
What context length does Loom Spark 3.2 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.0 GB at 8K and 0.0 GB at 2K.
Where can I download Loom Spark 3.2 GGUF?
The files are on Hugging Face in the textilelabs/Loom-Spark-3.2 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 Spark 3.2 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 Spark 3.2 on 8 GB VRAM?
Yes, the F16 quantization requires approximately 0.6 GB VRAM at 8k context, well within an 8 GB budget.
Does Loom Spark 3.2 support vision?
No, the model does not include vision capabilities.
What tools can Loom Spark 3.2 use?
The model is detected to support tool use, but specific tool integrations are not listed.