Lythri-7B-A4B needs about 8.1 GB of memory at Q6_K (a 6.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.7 GB (Q5_K_M) to 8.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Lythri‑7B‑A4B – a 7‑billion‑parameter Gemma4 model focused on emotional conversation
Lythri‑7B‑A4B is a 7‑billion‑parameter Gemma4 model trained for emotional companionship. It supports 131 072‑token context and is released under Apache 2.0. The model is optimized for natural, multi‑turn dialogue rather than math or coding tasks.
Good at
- Conversational emotional support
- Multi‑turn natural dialogue
- Low‑resource local deployment
Limits
- Not suited for complex math or coding
- No vision capabilities
- Requires 8 k context for memory estimates
Best for
- Chatbots needing emotional intelligence
- Personal companion apps
- Local LLM deployment on laptops
Who it’s for. Developers building conversational agents that prioritize emotional understanding. Users who need a lightweight, on‑device model for personal use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 5.7 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 6.2 GB | 8.1 GB | Too big | Get file → | |
| Q8_0 | 8.0 GB | 9.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q5_K_M (5.72 GB, ~7.6 GB RAM at 8 k context). For 10 GB VRAM, Q6_K (6.17 GB, ~8.1 GB RAM). For 12 GB VRAM, Q8_0 (7.97 GB, ~9.9 GB RAM). Estimates are approximate.
What GPU do you need for Lythri-7B-A4B?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
Which Lythri-7B-A4B quant should you choose?
Q6_K (6.2 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 5.7 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-7B-A4B
How much VRAM does Lythri-7B-A4B need?
About 8.1 GB at Q6_K with an 8K context window. That is the 6.2 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-7B-A4B on an 8 GB GPU?
Yes, with Q5_K_M: the 5.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Lythri-7B-A4B GGUF?
It depends on the quant: Q5_K_M is 5.7 GB, Q6_K is 6.2 GB, Q8_0 is 8.0 GB.
What context length does Lythri-7B-A4B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download Lythri-7B-A4B GGUF?
The files are on Hugging Face in the Lythri/Lythri-7B-A4B-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-7B-A4B 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‑7B‑A4B on 8 GB VRAM?
Yes, using the Q5_K_M quantization which requires about 7.6 GB of VRAM at 8 k context.
Does Lythri‑7B‑A4B support vision tasks?
No, the model is purely text‑based and has no vision capabilities.