SmolLM2-1.7B-telegram-chats — GGUF

a full SFT of SmolLM2-1.7B on 3,000 synthetic

Telegram Desktop export conversations, trained with TRL. The model writes chat histories in the

Telegram Desktop export (result.json) format.

Live demo: Offlin33er/telegram-chat-generator runs the Q4_K_M file on a free CPU Space.

Files

| File | Quant | Size |

|---|---|---|

| smollm2-1.7b-telegram-chats-f16.gguf | f16 (full precision) | 3.4 GB |

| smollm2-1.7b-telegram-chats-q4_k_m.gguf | Q4_K_M | 1.1 GB |

Drop a file into LM Studio or any llama.cpp-based runner and prompt it with

a Telegram-export style conversation. Typical use: generating synthetic chat data for fine-tuning

or testing chat-rendering pipelines.

SFT with TRL on

see the full-precision model card for the training procedure and framework versions.

Question 2

What license applies to Offlin33er/SmolLM2-1.7B-telegram-chats-GGUF?

Accepted Answer

License: apache-2.0. Verify terms on Hugging Face before commercial use.

Question 3

How do I run Offlin33er/SmolLM2-1.7B-telegram-chats-GGUF locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does Offlin33er/SmolLM2-1.7B-telegram-chats-GGUF need?

Accepted Answer

Runs locally from ~1006.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

File	Type	Quantization	Size	Link
smollm2-1.7b-telegram-chats-f16.gguf	GGUF	F16	3.19 GB	Download
smollm2-1.7b-telegram-chats-q4_k_m.gguf	GGUF	Q4_K_M	1006.7 MB	Download

Model ID	Offlin33er/SmolLM2-1.7B-telegram-chats-GGUF
Author	Offlin33er
Pipeline	text-generation
License	apache-2.0
Base model	HuggingFaceTB/SmolLM2-1.7B
Last modified	2026-09-24T12:54:45.000Z