What are the hardware requirements for TwIL LM?

TwIL LM requires approximately 1.1 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 TwIL LM and how large is it?

TwIL LM is developed by webAI-Official, a model with 1.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does TwIL LM perform on standard benchmarks?

TwIL LM has the following published scores: LMSYS ELO 1062. Compare against reference models on this page or on the LLM Explorer leaderboards.

TwIL LM by webAI-Official — VRAM 1.1GB, 8K context

Name: TwIL LM
Author: webAI-Official

TwIL LM is an open-source language model by webAI-Official. Features: 1.7b LLM, VRAM: 1.1GB, Context: 8K, License: other, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.41, ELO: 1062.

Merged Model Base model:adapter:huggingface... Base model:huggingfacetb/smoll... Conversational En Endpoints compatible Formal-logic Gguf Instruct Llama Llama.cpp Lora Peft Q8 Quantized Reasoning Region:us Smollm2 Twil-lm

Model Card on HF 🤗: https://huggingface.co/webAI-Official/TwIL-LM

TwIL LM Benchmarks

LMSys ELO 1062 vs 1272 (so35) -16.5%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

TwIL LM Parameters and Internals

LLM Name	TwIL LM
Repository 🤗	https://huggingface.co/webAI-Official/TwIL-LM
Base Model(s)	HuggingFaceTB/SmolLM2-1.7B-Instruct HuggingFaceTB/SmolLM2-1.7B-Instruct
Merged Model	Yes
Model Size	1.7b
Required VRAM	1.1 GB
Updated	2026-08-11
Maintainer	webAI-Official
Model Type	llama
Instruction-Based	Yes
Model Files	1.8 GB 1.1 GB 1.2 GB 3.4 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf\|q8\|q4_k\|q5_k
Model Architecture	LlamaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	49152
Torch Data Type	bfloat16
Errors	replace

Rank the TwIL LM 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 TwIL LM

Best Alternatives	Context / RAM	Downloads	Likes
SmolLM2 1.7B Merged	8K / 3.4 GB	22	0
SmolLM2 1.7B Instruct Q8 Mlx	8K / 1.8 GB	258	5
SmolLM2 1.7B Instruct Bnb 4bit	8K / 1 GB	407	2
SmolLM 1.7B Bnb 4bit	2K / 1 GB	34	2
SmolLM 1.7B Instruct 4bit	2K / 1 GB	70	2
SmolLM 1.7B Instruct 8bit	2K / 1.8 GB	9	1
SmolLM2 1.7B Instruct 16K	16K / 3.4 GB	103	10
SmolLM2 1.7B Instruct	8K / 3.4 GB	154013	742
SmolLM2 1.7B Instruct	8K / 3.4 GB	4909	6
...ygnis Alpha 1.7B V0.1 Instruct	8K / 3.4 GB	11	2