What are the hardware requirements for Digest Sft3?

Digest Sft3 requires approximately 0.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Digest Sft3 and how large is it?

Digest Sft3 is developed by usr-wwelsh, a model with 135m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Digest Sft3?

Digest Sft3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Digest Sft3 by usr-wwelsh — VRAM 0.1GB, 8K context

Name: Digest Sft3
Author: usr-wwelsh

Digest Sft3 is an open-source language model by usr-wwelsh. Features: 135m LLM, VRAM: 0.1GB, Context: 8K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.32.

Base model:huggingfacetb/smoll... Base model:quantized:huggingfa... Conversational Endpoints compatible Generated from trainer Gguf Instruct Llama Q8 Quantized Region:us Safetensors Sft Trl

Model Card on HF 🤗: https://huggingface.co/usr-wwelsh/digest-sft3

Digest Sft3 Parameters and Internals

LLM Name	Digest Sft3
Repository 🤗	https://huggingface.co/usr-wwelsh/digest-sft3
Base Model(s)	SmolLM2 135M Instruct HuggingFaceTB/SmolLM2-135M-Instruct
Model Size	135m
Required VRAM	0.1 GB
Updated	2026-08-26
Maintainer	usr-wwelsh
Model Type	llama
Instruction-Based	Yes
Model Files	0.1 GB 0.5 GB
GGUF Quantization	Yes
Quantization Type	q8\|gguf
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	5.15.1
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	49152
Errors	replace

Rank the Digest Sft3 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Digest Sft3

Best Alternatives	Context / RAM	Downloads	Likes
SmolLM2 135M Merged	8K / 0.3 GB	16	0
...5M Instruct Bnb 4bit Reasoning	8K / 0.3 GB	36	1
SmolLM2 135M Instruct Bnb 4bit	8K / 0.1 GB	652	5
SmolLM2 135M Instruct Q8 Mlx	8K / 0.1 GB	198	2
SmolLM 135M Instruct 4bit	2K / 0.1 GB	1538	6
SmolLM 135M Instruct Fp16	2K / 0.3 GB	32	2
SmolLM 135M Instruct 8bit	2K / 0.1 GB	15	2
Digest Sft2	8K / 0.5 GB	178	0
SmolLM2 135M Instruct	8K / 0.3 GB	1857297	388
SmolLM2 135M Reasoning 5K	8K / 0.3 GB	276	3