What are the hardware requirements for Q2.5 Veltha 14B 0.5?

Q2.5 Veltha 14B 0.5 requires approximately 29.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Q2.5 Veltha 14B 0.5 and how large is it?

Q2.5 Veltha 14B 0.5 is developed by djuna, a model with 14b 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 Q2.5 Veltha 14B 0.5?

Q2.5 Veltha 14B 0.5 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Q2.5 Veltha 14B 0.5 by djuna — VRAM 29.7GB, 128K context

Name: Q2.5 Veltha 14B 0.5
Author: djuna

Q2.5 Veltha 14B 0.5 is an open-source language model by djuna. Features: 14b LLM, VRAM: 29.7GB, Context: 128K, Instruction-Based, Merged, LLM Explorer Score: 0.28.

Merged Model Base model:allura-org/tq2.5-14... Base model:arcee-ai/supernova-... Base model:eva-unit-01/eva-qwe... Base model:huihui-ai/qwen2.5-1... Base model:v000000/qwen2.5-lum... Conversational Deploy:azure Endpoints compatible Instruct Model-index Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5

Q2.5 Veltha 14B 0.5 Parameters and Internals

LLM Name	Q2.5 Veltha 14B 0.5
Repository 🤗	https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5
Base Model(s)	SuperNova Medius huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2 allura-org/TQ2.5-14B-Aletheia-v1 EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2 v000000/Qwen2.5-Lumen-14B arcee-ai/SuperNova-Medius huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2 allura-org/TQ2.5-14B-Aletheia-v1 EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2 v000000/Qwen2.5-Lumen-14B
Merged Model	Yes
Model Size	14b
Required VRAM	29.7 GB
Updated	2026-08-07
Maintainer	djuna
Model Type	qwen2
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-6 5.0 GB: 2-of-6 5.0 GB: 3-of-6 5.0 GB: 4-of-6 5.0 GB: 5-of-6 4.8 GB: 6-of-6
Model Architecture	Qwen2ForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.46.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151665
Torch Data Type	bfloat16
Errors	replace

Rank the Q2.5 Veltha 14B 0.5 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 Q2.5 Veltha 14B 0.5

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 14B Instruct 1M	986K / 29.6 GB	10388	342
T3Q Qwen2.5 14B V1.0 E3	986K / 29.7 GB	852	28
ZYH LLM Qwen2.5 14B V4	986K / 29.7 GB	27	8
Qwen2.5 14B 1M YOYO V3	986K / 29.7 GB	254	4
Qwen2.5 14B YOYO V4	986K / 29.7 GB	20	5
Qwen2.5 14B YOYO Latest V2	986K / 29.7 GB	129	0
ZYH LLM Qwen2.5 14B V3	986K / 29.7 GB	23	8
...14B Instruct 1M GRPO Reasoning	986K / 29.7 GB	11	4
Impish QWEN 14B 1M	986K / 29.7 GB	56	26
Q2.5 14B Instruct 1M Harmony	986K / 29.7 GB	3	1

Note: green Score (e.g. "73.2") means that the model is better than djuna/Q2.5-Veltha-14B-0.5.