What are the hardware requirements for Quipu MoE 1B A149M Chat Distill?

Quipu MoE 1B A149M Chat Distill requires approximately 4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Quipu MoE 1B A149M Chat Distill and how large is it?

Quipu MoE 1B A149M Chat Distill is developed by AneekC, a model with 998m 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 Quipu MoE 1B A149M Chat Distill?

Quipu MoE 1B A149M Chat Distill is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Quipu MoE 1B A149M Chat Distill by AneekC — VRAM 4GB

Name: Quipu MoE 1B A149M Chat Distill
Author: AneekC

Quipu MoE 1B A149M Chat Distill is an open-source language model by AneekC. Features: 998m LLM, VRAM: 4GB, License: apache-2.0, MoE, LLM Explorer Score: 0.31.

Arxiv:2203.13474 Arxiv:2301.03988 Arxiv:2409.12186 Base model:aneekc/quipu-moe-1b... Base model:finetune:aneekc/qui... Code Conversational Dataset:codeparrot/apps Dataset:codeparrot/github-code... Dataset:cohereforai/aya datase... Dataset:huggingfacefw/fineweb-... Dataset:huggingfacefw/fineweb-... Dataset:nvidia/opencodeinstruc... Dataset:openassistant/oasst2 Distillation En From-scratch Hi Id Ja Ko Mixture-of-experts Moe Ms Multilingual Pytorch Region:us Safetensors Small-language-model Ta Ur Zh

Model Card on HF 🤗: https://huggingface.co/AneekC/quipu-moe-1B-A149M-chat-distill

Quipu MoE 1B A149M Chat Distill Parameters and Internals

LLM Name	Quipu MoE 1B A149M Chat Distill
Repository 🤗	https://huggingface.co/AneekC/quipu-moe-1B-A149M-chat-distill
Model Name	quipu-moe-1B-A149M-chat
Base Model(s)	Quipu MoE 1B A149M AneekC/quipu-moe-1B-A149M
Model Size	998m
Required VRAM	4 GB
Updated	2026-10-16
Maintainer	AneekC
Model Files	4.0 GB
Supported Languages	en id ms zh ja ko ta hi ur
License	apache-2.0
Model Max Length	2048
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	49152

Rank the Quipu MoE 1B A149M Chat Distill 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