What are the hardware requirements for Qwen3.8 27B Euskara?

Qwen3.8 27B Euskara requires approximately 55.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.8 27B Euskara and how large is it?

Qwen3.8 27B Euskara is developed by mikelalda, a model with 27b 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 Qwen3.8 27B Euskara?

Qwen3.8 27B Euskara is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.8 27B Euskara by mikelalda — VRAM 55.6GB

Name: Qwen3.8 27B Euskara
Author: mikelalda

Qwen3.8 27B Euskara is an open-source language model by mikelalda. Features: 27b LLM, VRAM: 55.6GB, License: cc-by-sa-4.0, Instruction-Based, LLM Explorer Score: 0.29.

Base model:adapter:unsloth/qwe... Base model:unsloth/qwen3.8-27b Basque Conversational Dataset:hitz/alia syntethic mt... Dataset:hitz/magpie-en-eu-reas... Dataset:hitz/rag eu En Endpoints compatible Es Eu Euskara Image-text-to-text Instruct Lora Peft Qwen3 5 Qwen3 8 Region:us Safetensors Sft Sharded Tensorflow Translation Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/mikelalda/qwen3.8-27b_euskara

Qwen3.8 27B Euskara Parameters and Internals

LLM Name	Qwen3.8 27b Euskara
Repository 🤗	https://huggingface.co/mikelalda/qwen3.8-27b_euskara
Model Name	unsloth/Qwen3.8-27B
Base Model(s)	unsloth/Qwen3.8-27B unsloth/Qwen3.8-27B
Model Size	27b
Required VRAM	55.6 GB
Updated	2026-08-21
Maintainer	mikelalda
Model Type	qwen3_5
Instruction-Based	Yes
Model Files	4.0 GB: 1-of-18 3.0 GB: 2-of-18 2.5 GB: 3-of-18 4.0 GB: 4-of-18 2.1 GB: 5-of-18 4.0 GB: 6-of-18 2.1 GB: 7-of-18 4.0 GB: 8-of-18 2.1 GB: 9-of-18 4.0 GB: 10-of-18 2.1 GB: 11-of-18 4.0 GB: 12-of-18 2.1 GB: 13-of-18 4.0 GB: 14-of-18 2.1 GB: 15-of-18 4.0 GB: 16-of-18 2.1 GB: 17-of-18 3.4 GB: 18-of-18
Supported Languages	eu es en
Model Architecture	Qwen3_5ForConditionalGeneration
License	cc-by-sa-4.0
Model Max Length	262144
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen3.8 27B Euskara 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 Qwen3.8 27B Euskara

Best Alternatives	Context / RAM	Downloads	Likes
...1 Darker Hero GAIN B Mxfp8 Mlx	0K / 28.7 GB	609	2
...sion GAIN V1.1 Fable Mxfp8 Mlx	0K / 28.7 GB	720	2
Qwen3.8 27B Brainwaves	0K / 55.5 GB	401	1
Tmax 27B	0K / 53.8 GB	4630	26
...en3.8 27B Brainwaves Mxfp8 Mlx	0K / 28.7 GB	361	1
...ble Fusion F711 GAIN Mxfp4 Mlx	0K / 15.1 GB	423	1
Qwen27b Alia Tuned	0K / 55.6 GB	19	0
...3.5 27B Claude 4.6 OS INSTRUCT	0K / 54.7 GB	1841	13
Droplychee 1.0 27B	0K / 55.4 GB	252480	2
...rchitect Polaris2 Fable B F451	0K / 55.5 GB	3867	23

Note: green Score (e.g. "73.2") means that the model is better than mikelalda/qwen3.8-27b_euskara.