What are the hardware requirements for Qwen3.5 104B A10b LegalReap?

Qwen3.5 104B A10b LegalReap requires approximately 208 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 Qwen3.5 104B A10b LegalReap and how large is it?

Qwen3.5 104B A10b LegalReap is developed by ProprietaryLegal, a model with 104b 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 Qwen3.5 104B A10b LegalReap?

Qwen3.5 104B A10b LegalReap is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 104B A10b LegalReap by ProprietaryLegal — VRAM 208GB, 256K context

Name: Qwen3.5 104B A10b LegalReap
Author: ProprietaryLegal

Qwen3.5 104B A10b LegalReap is an open-source language model by ProprietaryLegal. Features: 104b LLM, VRAM: 208GB, Context: 256K, License: apache-2.0, MoE, LLM Explorer Score: 0.24.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-122b-a... Conversational En Endpoints compatible Expert-pruning Legal-ai Legal-reasoning Mixture-of-experts Moe Qwen Qwen3.5 Qwen3 5 moe text Reap Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ProprietaryLegal/Qwen3.5-104b-a10b-LegalReap

Qwen3.5 104B A10b LegalReap Parameters and Internals

LLM Name	Qwen3.5 104B A10b LegalReap
Repository 🤗	https://huggingface.co/ProprietaryLegal/Qwen3.5-104b-a10b-LegalReap
Base Model(s)	Qwen/Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B
Model Size	104b
Required VRAM	208 GB
Updated	2026-08-06
Maintainer	ProprietaryLegal
Model Type	qwen3_5_moe_text
Model Files	47.3 GB: 1-of-5 49.9 GB: 2-of-5 48.3 GB: 3-of-5 49.9 GB: 4-of-5 12.6 GB: 5-of-5
Supported Languages	en
Model Architecture	Qwen3_5MoeForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.13.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the Qwen3.5 104B A10b LegalReap 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