Lythri-4B-A2B needs about 4.9 GB of memory at Q6_K (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.6 GB (Q5_K_M) to 4.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Lythri-4B-A2B: a small Gemma4 model for emotional conversation
Lythri-4B-A2B is a 4.63 billion‑parameter Gemma4 model focused on emotional companionship. It is trained to understand feelings and maintain natural multi‑turn dialogue while remaining lightweight enough for local deployment.
Good at
- Emotionally intelligent chat
- Low‑resource local inference
- Multi‑turn conversation
Limits
- Not suited for math or coding
- No vision support
- Requires Apache‑2.0 license
Best for
- Personal chatbot on a laptop
- Mental health support companion
- Lightweight conversational AI
Who it’s for. Developers building on‑device chat assistants that need emotional awareness. The model is ideal for mobile or edge devices where GPU memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 4.9 GB | 6.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q5_K_M (3.62 GB file, 4.7 GB memory). If 12 GB VRAM is available, Q6_K (3.83 GB file, 4.9 GB memory) is a good balance. For 16 GB or more, Q8_0 (4.95 GB file, 6 GB memory) gives the highest precision.
What GPU do you need for Lythri-4B-A2B?
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: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
Which Lythri-4B-A2B quant should you choose?
Q6_K (3.8 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q5_K_M at 3.6 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Lythri-4B-A2B
How much VRAM does Lythri-4B-A2B need?
About 4.9 GB at Q6_K with an 8K context window. That is the 3.8 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 Lythri-4B-A2B on an 8 GB GPU?
Yes, with Q8_0: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Lythri-4B-A2B GGUF?
It depends on the quant: Q5_K_M is 3.6 GB, Q6_K is 3.8 GB, Q8_0 is 4.9 GB.
What context length does Lythri-4B-A2B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download Lythri-4B-A2B GGUF?
The files are on Hugging Face in the Lythri/Lythri-4B-A2B-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 Lythri-4B-A2B 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 Lythri-4B-A2B on 8 GB VRAM?
Yes, the Q5_K_M quantization requires 4.7 GB of VRAM at 8 k context, which fits within 8 GB.
Does Lythri-4B-A2B support vision tasks?
No, the model is purely text‑based and has no vision capabilities.
What license applies to Lythri-4B-A2B?
The model is released under the Apache License 2.0.