LO

Loxa 1.6B

LoxaGGUF by mradermacherUpdated 2025-02-03
Download on Hugging Face
Parameters1.66B
Context128K
Layers23
Architecturellama
Smallest quant0.5 GB
Quick answer

Loxa 1.6B needs about 1.9 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.5 GB (IQ1_S) to 1.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.5 GB.

Loxa 1.6B – a 1.66B‑parameter conversational model

Loxa 1.6B is a 1.66B‑parameter llama‑based model trained on a large high‑quality text corpus. It is optimized for conversational tasks and supports tool usage. The model is released under the apache‑2.0 license.

Good at

  • High‑quality text generation
  • Strong English language understanding
  • Tool‑aware conversational AI

Limits

  • No vision support
  • Requires 131072 context tokens
  • Large VRAM needed for higher‑quality quants

Best for

  • Chatbots and virtual assistants
  • Interactive dialogue systems
  • Tool‑integrated task automation

Who it’s for. Developers and researchers building conversational AI applications who need a well‑trained, tool‑aware model. The model is suitable for CPU or GPU deployment with sufficient memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.5 GB 1.4 GB
Fits Get file →
IQ1_M0.5 GB 1.4 GB
Fits Get file →
IQ2_XXS0.6 GB 1.4 GB
Fits Get file →
IQ2_XS0.6 GB 1.5 GB
Fits Get file →
IQ2_S0.6 GB 1.5 GB
Fits Get file →
IQ2_M0.7 GB 1.5 GB
Fits Get file →
Q2_K_S0.7 GB 1.6 GB
Fits Get file →
IQ3_XXS0.7 GB 1.6 GB
Fits Get file →
Q2_K0.7 GB 1.6 GB
Fits Get file →
IQ3_XS0.8 GB 1.7 GB
Fits Get file →
Q3_K_S0.8 GB 1.7 GB
Fits Get file →
IQ3_S0.8 GB 1.7 GB
Fits Get file →
IQ3_M0.8 GB 1.7 GB
Fits Get file →
Q3_K_M0.9 GB 1.8 GB
Fits Get file →
Q3_K_L1.0 GB 1.8 GB
Fits Get file →
IQ4_XS1.0 GB 1.9 GB
Fits Get file →
Q4_01.0 GB 1.9 GB
Fits Get file →
IQ4_NL1.0 GB 1.9 GB
Fits Get file →
Q4_K_S1.0 GB 1.9 GB
Fits Get file →
Q4_K_M1.1 GB 1.9 GB
Fits Get file →
Q4_11.1 GB 2.0 GB
Fits Get file →
Q5_K_S1.2 GB 2.1 GB
Fits Get file →
Q5_K_M1.2 GB 2.1 GB
Fits Get file →
Q6_K1.4 GB 2.3 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (0.48 GB or 0.51 GB). For 12 GB VRAM, IQ2_XS or IQ2_S (0.6 GB or 0.62 GB) are suitable. For 16 GB VRAM, Q4_K_M (1.06 GB) or Q5_K_M (1.21 GB) provide higher quality. Memory estimates are approximate.

What GPU do you need for Loxa 1.6B?

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 Q6_K (1.4 GB file, about 2.3 GB in use).

Which Loxa 1.6B quant should you choose?

Q4_K_M is the usual starting point for Loxa 1.6B: it balances file size and quality well. Here it is a 1.1 GB file.

If memory is tight, the smallest file is IQ1_S at 0.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.66B
Layers23
Trained context131,072 tokens
KV cache (fp16)46 KB per token

Source

Quantized bymradermacher
FamilyLoxa
Licenseapache-2.0
Downloads (HF)616
Last updated2025-02-03

Frequently asked questions about Loxa 1.6B

How much VRAM does Loxa 1.6B need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Loxa 1.6B on an 8 GB GPU?

Yes, with Q6_K: the 1.4 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Loxa 1.6B GGUF?

It depends on the quant: IQ1_S is 0.5 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.6 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB, IQ2_M is 0.7 GB and 18 more.

What context length does Loxa 1.6B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.5 GB at 32K.

Where can I download Loxa 1.6B GGUF?

The files are on Hugging Face in the mradermacher/Loxa-1.6B-uncensored-i1-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 Loxa 1.6B 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 Loxa 1.6B on 8 GB VRAM?

Yes, the smallest quants IQ1_S and IQ1_M fit within 8 GB VRAM, using about 1.4 GB of memory at 8k context.

Does Loxa 1.6B support image inputs?

No, the model does not include vision capabilities.

What license applies to Loxa 1.6B?

The model is released under the apache‑2.0 license.

Other GGUFs of Loxa-1.6B-uncensored

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Loxa models

All Loxa →

Other tiny models

All tiny models →