What are the hardware requirements for E3 1.7B?

E3 1.7B requires approximately 3.4 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed E3 1.7B and how large is it?

E3 1.7B is developed by CMU-AIRe, 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 E3 1.7B perform on standard benchmarks?

E3 1.7B has the following published scores: LMSYS ELO 272. Compare against reference models on this page or on the LLM Explorer leaderboards.

E3 1.7B by CMU-AIRe — VRAM 3.4GB, 40K context

Name: E3 1.7B
Author: CMU-AIRe

E3 1.7B is an open-source language model by CMU-AIRe. Features: 1.7b LLM, VRAM: 3.4GB, Context: 40K, License: mit, LLM Explorer Score: 0.21, ELO: 272.

Dataset:cmu-aire/e3-math-easy Dataset:cmu-aire/e3-math-medha... Dataset:cmu-aire/hmmt-aime-202... Qwen3 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/CMU-AIRe/e3-1.7B

E3 1.7B Benchmarks

LMSys ELO 272 vs 1272 (so35) -78.6%

^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)

E3 1.7B Parameters and Internals

LLM Name	E3 1.7B
Repository 🤗	https://huggingface.co/CMU-AIRe/e3-1.7B
Model Size	1.7b
Required VRAM	3.4 GB
Updated	2026-09-12
Maintainer	CMU-AIRe
Model Type	qwen3
Model Files	3.4 GB
Model Architecture	Qwen3ForCausalLM
License	mit
Context Length	40960
Model Max Length	40960
Transformers Version	4.51.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the E3 1.7B 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 E3 1.7B

Best Alternatives	Context / RAM	Downloads	Likes
Lucy 128K	128K / 3.4 GB	123	112
Polaris 1.7B Preview	128K / 3.4 GB	73	8
DictaLM 3.0 1.7B Instruct	60K / 3.4 GB	2842	1
Qwen3 1.7B	40K / 4 GB	5633291	500
RIFA FLASH 1.7B	40K / 3.4 GB	583	0
DualMind TKD Agentic 1.7B	40K / 3.4 GB	1798	0
Atomight V2.5 1.7B	40K / 3.4 GB	1406	1
Qwen3 1.7B Base MED ChatVector	40K / 3.4 GB	204	1
MedPsy 1.7B	40K / 4.1 GB	933	8
Jibay 2	40K / 4 GB	356	3

Note: green Score (e.g. "73.2") means that the model is better than CMU-AIRe/e3-1.7B.