What are the hardware requirements for Drex V1.5?

Drex V1.5 requires approximately 17.9 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 Drex V1.5 and how large is it?

Drex V1.5 is developed by nace-ai, a model with 9b 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 Drex V1.5?

Drex V1.5 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Drex V1.5 by nace-ai — VRAM 17.9GB, 256K context

Name: Drex V1.5
Author: nace-ai

Drex V1.5 is an open-source language model by nace-ai. Features: 9b LLM, VRAM: 17.9GB, Context: 256K, License: other, LLM Explorer Score: 0.35.

Base model:finetune:xiaomimimo... Base model:xiaomimimo/mimo-v2.... Decision-model Drex Kev Qwen3 5 text Region:us Safetensors Sharded System-one Tensorflow

Model Card on HF 🤗: https://huggingface.co/nace-ai/drex-v1.5

Drex V1.5 Parameters and Internals

LLM Name	Drex V1.5
Repository 🤗	https://huggingface.co/nace-ai/drex-v1.5
Base Model(s)	XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Model Size	9b
Required VRAM	17.9 GB
Updated	2026-10-13
Maintainer	nace-ai
Model Type	qwen3_5_text
Model Files	0.0 GB 4.9 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 3.0 GB: 4-of-4
Model Architecture	Qwen3_5ForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	5.17.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the Drex V1.5 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 Drex V1.5

Best Alternatives	Context / RAM	Downloads	Likes
...thos 9B V2 Heretic Abliterated	1024K / 17.9 GB	80	3
Le Gros Chaton	256K / 17.9 GB	235	1
NeoHorse 1 9B	256K / 18 GB	1250	196
...yber Ornith 1.5 9B OBLITERATED	256K / 17.9 GB	1424	7
JEV 9B	256K / 17.8 GB	471	12
WikiQwen 9B	256K / 17.9 GB	1039	0
...te Qwopus MiMo Ornith 9B Coder	256K / 17.8 GB	537	6
JevK5 9B	256K / 17.9 GB	683	1
Sbsam	256K / 17.9 GB	171	2
Qwen3.5 9B OutsideTheBox SFT	256K / 17.9 GB	409	0

Note: green Score (e.g. "73.2") means that the model is better than nace-ai/drex-v1.5.