What are the hardware requirements for Mini K3 1H Llama Gqa Standard V1?

Mini K3 1H Llama Gqa Standard V1 requires approximately 1.9 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mini K3 1H Llama Gqa Standard V1 and how large is it?

Mini K3 1H Llama Gqa Standard V1 is developed by nkkbr, a model with 966.3m 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 Mini K3 1H Llama Gqa Standard V1?

Mini K3 1H Llama Gqa Standard V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mini K3 1H Llama Gqa Standard V1 by nkkbr — VRAM 1.9GB, 128K context

Name: Mini K3 1H Llama Gqa Standard V1
Author: nkkbr

Mini K3 1H Llama Gqa Standard V1 is an open-source language model by nkkbr. Features: 966.3m LLM, VRAM: 1.9GB, Context: 128K, LLM Explorer Score: 0.35.

Architecture-ablation Kimi-k3 Llama-style-attention Mini k3 Mixture-of-experts Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/nkkbr/Mini-K3-1H-llama-gqa-standard-v1

Mini K3 1H Llama Gqa Standard V1 Parameters and Internals

LLM Name	Mini K3 1H Llama Gqa Standard V1
Repository 🤗	https://huggingface.co/nkkbr/Mini-K3-1H-llama-gqa-standard-v1
Model Name	Mini-K3-1H-llama-gqa-standard
Model Size	966.3m
Required VRAM	1.9 GB
Updated	2026-09-28
Maintainer	nkkbr
Model Type	mini_k3
Model Files	1.9 GB
Context Length	131072
Model Max Length	131072
Tokenizer Class	TikTokenTokenizer
Padding Token	[PAD]
Vocabulary Size	163840

Rank the Mini K3 1H Llama Gqa Standard V1 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