What are the hardware requirements for Instruct Igel 001?

Instruct Igel 001 requires approximately 12.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Instruct Igel 001 and how large is it?

Instruct Igel 001 is developed by philschmid. 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 Instruct Igel 001?

Instruct Igel 001 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Instruct Igel 001 by philschmid — VRAM 12.9GB

Name: Instruct Igel 001
Author: philschmid

Instruct Igel 001 is an open-source language model by philschmid. Features: LLM, VRAM: 12.9GB, License: bigscience-openrail-m, Instruction-Based, LLM Explorer Score: 0.06.

Bloom De Deploy:azure Instruct Lora Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/philschmid/instruct-igel-001

Instruct Igel 001 Parameters and Internals

Model Type

text generation, instruction-tuned

Additional Notes

Designed to evaluate instruction-based model creation with minimal training and naive translated data.

Supported Languages

German (Proficient)

Training Details

Data Sources:

naive translated instruction datasets

Methodology:

LoRA tuning with merged weights

Model Architecture:

BLOOM-CLP German

LLM Name	Instruct Igel 001
Repository 🤗	https://huggingface.co/philschmid/instruct-igel-001
Required VRAM	12.9 GB
Updated	2026-07-23
Maintainer	philschmid
Instruction-Based	Yes
Model Files	0.0 GB 9.9 GB: 1-of-2 3.0 GB: 2-of-2
Supported Languages	de
Model Architecture	AutoModelForCausalLM
License	bigscience-openrail-m
Is Biased	none
Tokenizer Class	GPT2Tokenizer
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	query_key_value
LoRA Alpha	32
LoRA Dropout	0.05
R Param	8

Rank the Instruct Igel 001 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 Instruct Igel 001

Best Alternatives	Context / RAM	Downloads	Likes
VLM2Vec LoRA	0K / 0 GB	96	11
... Mini 4K Instruct Chinese Lora	0K / 0 GB	8	6
Falcon Camel Math Instruct	0K / 0 GB	2	1
...emo Instruct 2407 EXL2 8bpw H8	0K / 12.6 GB	7	7
Dre Phi	0K / 7.6 GB	7	0
Phi 3 Mini 4K CodeInstruct	0K / 7.6 GB	10	0
...3 Mini 4K Instruct Text To Sql	0K / 7.6 GB	12	0
Phi 3 Mini 4K Python	0K / 7.6 GB	632	1
Pipi	0K / 2.4 GB	13	0

Note: green Score (e.g. "73.2") means that the model is better than philschmid/instruct-igel-001.