What are the hardware requirements for Midm 2.0 Base Instruct?

Midm 2.0 Base Instruct requires approximately 23.1 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Midm 2.0 Base Instruct and how large is it?

Midm 2.0 Base Instruct is developed by K-intelligence, a model with 11.5b 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 Midm 2.0 Base Instruct?

Midm 2.0 Base Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Midm 2.0 Base Instruct by K-intelligence — VRAM 23.1GB, 32K context

Name: Midm 2.0 Base Instruct
Author: K-intelligence

Midm 2.0 Base Instruct is an open-source language model by K-intelligence. Features: 11.5b LLM, VRAM: 23.1GB, Context: 32K, License: mit, Instruction-Based, LLM Explorer Score: 0.25.

Conversational En Endpoints compatible Instruct K-intelligence Ko Kt Llama Mi:dm Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/K-intelligence/Midm-2.0-Base-Instruct

Midm 2.0 Base Instruct Parameters and Internals

LLM Name	Midm 2.0 Base Instruct
Repository 🤗	https://huggingface.co/K-intelligence/Midm-2.0-Base-Instruct
Model Size	11.5b
Required VRAM	23.1 GB
Updated	2026-07-12
Maintainer	K-intelligence
Model Type	llama
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-5 5.0 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 3.4 GB: 5-of-5
Supported Languages	en ko
Model Architecture	LlamaForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.51.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	131384
Torch Data Type	bfloat16

Rank the Midm 2.0 Base Instruct 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 Midm 2.0 Base Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3 Monika Ddlc 11.5B V1	8K / 23 GB	25	3
Llama 3 11.5B Instruct V2	8K / 23 GB	7	6