Downloads · 30 days
17
12% of all-time downloads
llama32-3b-emo-gguf
T3cmit0/llama32-3b-emo-gguf
llama32-3b-emo-gguf is a text generation model from T3cmit0. Use it when you need the model to write or continue text. The card lists the license as llama3.2.
Fine-tune of Llama 3.2 3B Instruct for warm, emotionally supportive conversation in English, quantized to GGUF Q4KM for on-device inference with llama.cpp.
All-time downloads
143
Public
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2 GB · 100%
At a glance
- Task
- Text Generation
- License
- llama3.2
- Access
- Public
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026
- SHA
- ee0b0b96
Try a prompt
Base models
Model card
From the Hugging Face model README
Llama 3.2 3B — Emotional Support (GGUF)
Fine-tune of Llama 3.2 3B Instruct for warm, emotionally supportive conversation in English, quantized to GGUF Q4_K_M for on-device inference with llama.cpp.
These weights power Demo Chat, a fully offline Android chatbot —
source code: https://github.com/T3cm0/Chatbot_Movil_Proyecto
Model details
| Base model | unsloth/llama-3.2-3b-instruct-bnb-4bit |
| Fine-tuning | SFT with Unsloth + TRL, 2,000 steps |
| Domain | Emotionally supportive conversation (English) |
| File | llama32-3b-emo-Q4_K_M.gguf (~1.9 GB) |
| Context window used on device | 2,048 tokens |
| Recommended sampling | temp 0.6 · top_p 0.9 · top_k 40 |
Usage (llama.cpp)
llama-cli -m llama32-3b-emo-Q4_K_M.gguf -c 2048 --temp 0.6 --top-p 0.9
The model uses the standard Llama 3 chat template.
Conversion pipeline
bnb-4bit → fp16 (dequantize) → GGUF f16 (convert_hf_to_gguf.py) → Q4_K_M (llama-quantize). Note: transformers must be pinned to 4.49.0 for the
dequantization step.
⚠️ Q4_0 quantizations of this model produced incoherent output with
llama-quantizebuild b10488 (reproduced on x86-64 and ARM). Use Q4_K_M.
License
Derivative of Llama 3.2 — distributed under the Llama 3.2 Community License. Built with Llama.
- Task
- Text Generation
- License
- llama3.2
- Languages
- en
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026