What are the hardware requirements for Kolibri 1 MLX 4bit?

Kolibri 1 MLX 4bit requires approximately 44.1 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kolibri 1 MLX 4bit and how large is it?

Kolibri 1 MLX 4bit is developed by velaia, a model with 78.1b 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 Kolibri 1 MLX 4bit?

Kolibri 1 MLX 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kolibri 1 MLX 4bit by velaia — VRAM 44.1GB, 256K context

Name: Kolibri 1 MLX 4bit
Author: velaia

Kolibri 1 MLX 4bit is an open-source language model by velaia. Features: 78.1b LLM, VRAM: 44.1GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.34.

4-bit 4bit Apple-silicon Base model:aleph-alpha/kolibri... Base model:quantized:aleph-alp... Conversational De En Kolibri1 Mlx Moe Quantized Reasoning Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/velaia/Kolibri-1-MLX-4bit

Kolibri 1 MLX 4bit Parameters and Internals

LLM Name	Kolibri 1 MLX 4bit
Repository 🤗	https://huggingface.co/velaia/Kolibri-1-MLX-4bit
Base Model(s)	Kolibri 1 Aleph-Alpha/Kolibri-1
Model Size	78.1b
Required VRAM	44.1 GB
Updated	2026-10-07
Maintainer	velaia
Model Type	kolibri1
Model Files	5.3 GB: 1-of-9 5.2 GB: 2-of-9 5.2 GB: 3-of-9 5.2 GB: 4-of-9 5.2 GB: 5-of-9 5.2 GB: 6-of-9 5.2 GB: 7-of-9 5.2 GB: 8-of-9 2.4 GB: 9-of-9
Supported Languages	de en
Quantization Type	4bit
Model Architecture	Kolibri1ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Vocabulary Size	128000
Errors	replace

Rank the Kolibri 1 MLX 4bit 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 Kolibri 1 MLX 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Kolibri 1 MLX 3bit	256K / 35.1 GB	1126	3
Kolibri 1 MLX 6bit	256K / 63.1 GB	944	2
Kolibri 1	256K / 78.8 GB	4138	721
Kolibri 1 BF16	256K / 156.3 GB	862	51
Kolibri 1 Mlx Mixed 4 8 Bit	256K / 44.9 GB	1341	5
Kolibri 1	256K / 78.8 GB	107	1

Note: green Score (e.g. "73.2") means that the model is better than velaia/Kolibri-1-MLX-4bit.