What are the hardware requirements for Falcon H1 Tiny Coder 90M 8bit?

Falcon H1 Tiny Coder 90M 8bit requires approximately 0.1 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 Falcon H1 Tiny Coder 90M 8bit and how large is it?

Falcon H1 Tiny Coder 90M 8bit is developed by mlx-community, a model with 90m 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 Falcon H1 Tiny Coder 90M 8bit?

Falcon H1 Tiny Coder 90M 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Falcon H1 Tiny Coder 90M 8bit by mlx-community — VRAM 0.1GB, 256K context

Name: Falcon H1 Tiny Coder 90M 8bit
Author: mlx-community

Falcon H1 Tiny Coder 90M 8bit is an open-source language model by mlx-community. Features: 90m LLM, VRAM: 0.1GB, Context: 256K, License: other, Quantized, Code Generating, LLM Explorer Score: 0.22.

8-bit 8bit Base model:quantized:tiiuae/fa... Base model:tiiuae/falcon-h1-ti... Codegen Edge Falcon-h1 Falcon h1 Mlx Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/mlx-community/Falcon-H1-Tiny-Coder-90M-8bit

Falcon H1 Tiny Coder 90M 8bit Parameters and Internals

LLM Name	Falcon H1 Tiny Coder 90M 8bit
Repository 🤗	https://huggingface.co/mlx-community/Falcon-H1-Tiny-Coder-90M-8bit
Base Model(s)	Falcon H1 Tiny Coder 90M tiiuae/Falcon-H1-Tiny-Coder-90M
Model Size	90m
Required VRAM	0.1 GB
Updated	2026-08-10
Maintainer	mlx-community
Model Type	falcon_h1
Model Files	0.1 GB
Quantization Type	8bit
Generates Code	Yes
Model Architecture	FalconH1ForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	4.57.3
Tokenizer Class	TokenizersBackend
Vocabulary Size	32768

Rank the Falcon H1 Tiny Coder 90M 8bit 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 Falcon H1 Tiny Coder 90M 8bit

Best Alternatives	Context / RAM	Downloads	Likes
Falcon H1 Tiny Coder 90M	256K / 0.2 GB	120	11

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Falcon-H1-Tiny-Coder-90M-8bit.