SZL Khipu 1.5B needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.0 GB (Q4_K_M) to 3.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
Compact 1.5B Qwen2.5 fine‑tune for proposal‑only retrieval plans
SZL Khipu 1.5B is a 1.5 B‑parameter Qwen2.5 fine‑tune that generates JSON proposals over controller‑supplied handles. It is released under Apache‑2.0 and is intended for research and prototype use only.
Good at
- Proposal‑only retrieval plan generation
- JSON‑formatted output
- Small model footprint
Limits
- No vision or execution support
- Release blocked for production use
- Requires exact GGUF revision and compatible runtime
Best for
- Research on retrieval‑plan generation
- Low‑resource inference demos
- Prototype controller integration
Who it’s for. Researchers and developers building retrieval‑based systems who need a lightweight model to generate proposal plans. The model is not intended for production deployment or autonomous execution.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.4 GB | Fits | Get file → | |
| F16 | 3.1 GB | 3.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.99 GB, ~1.7 GB RAM at 8k context). For 12 GB VRAM, Q5_K_M (1.13 GB, ~1.9 GB RAM). Higher precision Q8_0 or F16 requires more memory and is not recommended for limited GPU budgets.
What GPU do you need for SZL Khipu 1.5B?
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 (3.1 GB file, about 3.8 GB in use).
Which SZL Khipu 1.5B quant should you choose?
Q4_K_M is the usual starting point for SZL Khipu 1.5B: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.6 GB, about 1.7 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
Source
Frequently asked questions about SZL Khipu 1.5B
How much VRAM does SZL Khipu 1.5B need?
About 1.7 GB at Q4_K_M 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 SZL Khipu 1.5B on an 8 GB GPU?
Yes, with F16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SZL Khipu 1.5B GGUF?
It depends on the quant: Q4_K_M is 1.0 GB, Q5_K_M is 1.1 GB, Q8_0 is 1.6 GB, F16 is 3.1 GB.
What context length does SZL Khipu 1.5B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download SZL Khipu 1.5B GGUF?
The files are on Hugging Face in the SZLHOLDINGS/SZL-Khipu-1.5B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SZL Khipu 1.5B 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 SZL Khipu 1.5B on 8 GB VRAM?
Yes, the Q4_K_M quantization uses about 1.7 GB of VRAM at 8k context, fitting comfortably on an 8 GB GPU.
Does this model support vision or image input?
No, the model is text‑only and does not process visual data.
Under what license is SZL Khipu 1.5B released?
It is released under the Apache‑2.0 license.