What are the hardware requirements for BigBang Aquila 35B Merged?

BigBang Aquila 35B Merged requires approximately 70.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed BigBang Aquila 35B Merged and how large is it?

BigBang Aquila 35B Merged is developed by osk-arr00, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does BigBang Aquila 35B Merged perform on standard benchmarks?

BigBang Aquila 35B Merged has the following published scores: LMSYS ELO 1395. Compare against reference models on this page or on the LLM Explorer leaderboards.

BigBang Aquila 35B Merged by osk-arr00 — VRAM 70.3GB

Name: BigBang Aquila 35B Merged
Author: osk-arr00

BigBang Aquila 35B Merged is an open-source language model by osk-arr00. Features: 35b LLM, VRAM: 70.3GB, License: apache-2.0, Quantized, Merged, LLM Explorer Score: 0.43, ELO: 1395.

Merged Model Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3... Conversational Endpoints compatible Gguf Image-text-to-text Quantized Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/osk-arr00/BigBang-Aquila-35B-Merged

BigBang Aquila 35B Merged Benchmarks

LMSys ELO 1395 vs 1272 (so35) 9.7%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

BigBang Aquila 35B Merged Parameters and Internals

LLM Name	BigBang Aquila 35B Merged
Repository 🤗	https://huggingface.co/osk-arr00/BigBang-Aquila-35B-Merged
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Merged Model	Yes
Model Size	35b
Required VRAM	70.3 GB
Updated	2026-08-22
Maintainer	osk-arr00
Model Type	qwen3_5_moe
Model Files	2.0 GB 4.3 GB: 1-of-16 4.5 GB: 2-of-16 5.0 GB: 3-of-16 4.0 GB: 4-of-16 4.5 GB: 5-of-16 5.0 GB: 6-of-16 4.0 GB: 7-of-16 5.0 GB: 8-of-16 4.5 GB: 9-of-16 5.0 GB: 10-of-16 4.0 GB: 11-of-16 4.5 GB: 12-of-16 5.0 GB: 13-of-16 4.0 GB: 14-of-16 4.5 GB: 15-of-16 2.5 GB: 16-of-16
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.12.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the BigBang Aquila 35B Merged 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 BigBang Aquila 35B Merged

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 35B A3B GGUF	0K / 0.9 GB	135718	862
...35B A3B NSC ACE SABER GGUF MTP	0K / 0.9 GB	20997	20
AgentWorld 35B A3B Heretic	0K / 70.4 GB	0	1
Darwin 35B A3B Opus Q8 GGUF	0K / 10.7 GB	289	25
Qwen3.6 35B A3B MLX 4bit	0K / 20.5 GB	513193	6
Qwen3.6 35B A3B MLX 6bit	0K / 28.9 GB	478592	2
Qwen3.6 35B A3B MLX 8bit	0K / 37.8 GB	473537	1
Qwen3.6 35B A3B UD MLX 4bit	0K / 21.6 GB	15720	112
Nail Qwen3.6 35B A3B MLX 5bit	0K / 27.5 GB	83	1
Qwen3.6 35B A3B MLX 8bit	0K / 37.8 GB	3862	41

Note: green Score (e.g. "73.2") means that the model is better than osk-arr00/BigBang-Aquila-35B-Merged.