What are the hardware requirements for 6 1?

6 1 requires approximately 3.3 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed 6 1 and how large is it?

6 1 is developed by ThreeZ, a model with 1.6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does 6 1 perform on standard benchmarks?

6 1 has the following published scores: LMSYS ELO 226. Compare against reference models on this page or on the LLM Explorer leaderboards.

6 1 by ThreeZ — VRAM 3.3GB, 4K context

Name: 6 1
Author: ThreeZ

6 1 is an open-source language model by ThreeZ. Features: 1.6b LLM, VRAM: 3.3GB, Context: 4K, LLM Explorer Score: 0.15, ELO: 226.

Arxiv:1910.09700 Conversational Endpoints compatible Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/ThreeZ/6_1

6 1 Benchmarks

LMSys ELO 226 vs 1272 (so35) -82.2%

^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)

6 1 Parameters and Internals

LLM Name	6 1
Repository 🤗	https://huggingface.co/ThreeZ/6_1
Model Size	1.6b
Required VRAM	3.3 GB
Updated	2026-07-23
Maintainer	ThreeZ
Model Type	llama
Model Files	3.3 GB
Model Architecture	LlamaForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the 6 1 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 6 1

Best Alternatives	Context / RAM	Downloads	Likes
1.5 Pints 16K V0.1	16K / 3.1 GB	57	16
Fox 1 1.6B	8K / 3.3 GB	23	33
Fox 1 1.6B Instruct V0.1	8K / 3.3 GB	12	14
Subnet6 001	8K / 16.1 GB	5	0
6 2	4K / 3.3 GB	136	0
Model 6	4K / 3.3 GB	66	0
Mymodel	4K / 3.3 GB	7	0
SN6	4K / 3.3 GB	6	0
Chuxin 1.6B Base	4K / 3.3 GB	17	16
Chuxin 1.6B 1M	4K / 3.3 GB	11	11

Note: green Score (e.g. "73.2") means that the model is better than ThreeZ/6_1.