What are the hardware requirements for Allosaurus V0.1 125B A6B JANGH2?

Allosaurus V0.1 125B A6B JANGH2 requires approximately 78.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Allosaurus V0.1 125B A6B JANGH2 and how large is it?

Allosaurus V0.1 125B A6B JANGH2 is developed by OsaurusAI, a model with 125b 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 Allosaurus V0.1 125B A6B JANGH2?

Allosaurus V0.1 125B A6B JANGH2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Allosaurus V0.1 125B A6B JANGH2 by OsaurusAI — VRAM 78.4GB

Name: Allosaurus V0.1 125B A6B JANGH2
Author: OsaurusAI

Allosaurus V0.1 125B A6B JANGH2 is an open-source language model by OsaurusAI. Features: 125b LLM, VRAM: 78.4GB, License: other, LLM Explorer Score: 0.28.

8-bit Agent Apple-silicon Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-... Conversational En Gptq Image-text-to-text Imatrix Jang Jangh Mlx Moe Mtp Quantized Qwen4 exp Reasoning Region:us Safetensors Sharded Tensorflow Thinking Tool-use Video Vision

Model Card on HF 🤗: https://huggingface.co/OsaurusAI/Allosaurus-v0.1-125B-A6B-JANGH2

Allosaurus V0.1 125B A6B JANGH2 Parameters and Internals

LLM Name	Allosaurus V0.1 125B A6B JANGH2
Repository 🤗	https://huggingface.co/OsaurusAI/Allosaurus-v0.1-125B-A6B-JANGH2
Base Model(s)	Qwen/Qwen3.8-Flash-Next Qwen/Qwen3.8-Flash-Next
Model Size	125b
Required VRAM	78.4 GB
Updated	2026-10-08
Maintainer	OsaurusAI
Model Type	qwen4_exp
Model Files	5.4 GB: 1-of-65 5.4 GB: 2-of-65 5.4 GB: 3-of-65 5.4 GB: 4-of-65 5.4 GB: 5-of-65 5.4 GB: 6-of-65 5.4 GB: 7-of-65 5.4 GB: 8-of-65 5.4 GB: 9-of-65 5.4 GB: 10-of-65 4.3 GB: 11-of-65 0.7 GB: 12-of-65 0.7 GB: 13-of-65 0.7 GB: 14-of-65 0.7 GB: 15-of-65 2.6 GB: 16-of-65 0.3 GB: 17-of-65 0.6 GB: 18-of-65 0.6 GB: 19-of-65 0.6 GB: 20-of-65 0.6 GB: 21-of-65 0.6 GB: 22-of-65 0.6 GB: 23-of-65 0.6 GB: 24-of-65 0.6 GB: 25-of-65 0.6 GB: 26-of-65 0.6 GB: 27-of-65 0.6 GB: 28-of-65 0.6 GB: 29-of-65 0.6 GB: 30-of-65 0.6 GB: 31-of-65 0.6 GB: 32-of-65 0.6 GB: 33-of-65 0.6 GB: 34-of-65 0.6 GB: 35-of-65 0.6 GB: 36-of-65 0.6 GB: 37-of-65 0.6 GB: 38-of-65 0.6 GB: 39-of-65 0.6 GB: 40-of-65 0.6 GB: 41-of-65
Supported Languages	en
Model Architecture	Qwen4ExpForConditionalGeneration
License	other
Transformers Version	5.8.0.dev0

Rank the Allosaurus V0.1 125B A6B JANGH2 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 Allosaurus V0.1 125B A6B JANGH2

Best Alternatives	Context / RAM	Downloads	Likes
...h Next MTPLX Optimized Quality	0K / 134.5 GB	1160	1

Note: green Score (e.g. "73.2") means that the model is better than OsaurusAI/Allosaurus-v0.1-125B-A6B-JANGH2.