What are the hardware requirements for Drafter Mixed Ut?

Drafter Mixed Ut requires approximately 0.3 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Drafter Mixed Ut and how large is it?

Drafter Mixed Ut is developed by MikhailRudenko, a model with 150m 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 Drafter Mixed Ut?

Drafter Mixed Ut is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Drafter Mixed Ut by MikhailRudenko — VRAM 0.3GB, 2K context

Name: Drafter Mixed Ut
Author: MikhailRudenko

Drafter Mixed Ut is an open-source language model by MikhailRudenko. Features: 150m LLM, VRAM: 0.3GB, Context: 2K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.25.

Instruct Knowledge-distillation Mistral Region:us Safetensors Speculative-decoding

Model Card on HF 🤗: https://huggingface.co/MikhailRudenko/drafter-mixed-ut

Drafter Mixed Ut Parameters and Internals

LLM Name	Drafter Mixed Ut
Repository 🤗	https://huggingface.co/MikhailRudenko/drafter-mixed-ut
Base Model(s)	Lite-Mistral-150M-v2-Instruct /Lite-Mistral-150M-v2-Instruct
Model Size	150m
Required VRAM	0.3 GB
Updated	2026-09-14
Maintainer	MikhailRudenko
Model Type	mistral
Instruction-Based	Yes
Model Files	0.3 GB 0.0 GB
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	5.11.0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32768

Rank the Drafter Mixed Ut 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 Drafter Mixed Ut

Best Alternatives	Context / RAM	Downloads	Likes
Mistral 150M Instruct	32K / 0.7 GB	6	0
Lite Mistral 150M V2 Instruct	2K / 0.6 GB	87	47
Sigmer 150M	2K / 0.3 GB	35	1
BabyHercules 150M	2K / 0.3 GB	24	0