What are the hardware requirements for Selfrl Fullfiles I49?

Selfrl Fullfiles I49 requires approximately 137.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Selfrl Fullfiles I49 and how large is it?

Selfrl Fullfiles I49 is developed by sweagent, a model with 35b 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 Selfrl Fullfiles I49?

Selfrl Fullfiles I49 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Selfrl Fullfiles I49 by sweagent — VRAM 137.1GB

Name: Selfrl Fullfiles I49
Author: sweagent

Selfrl Fullfiles I49 is an open-source language model by sweagent. Features: 35b LLM, VRAM: 137.1GB, License: apache-2.0, LLM Explorer Score: 0.28.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-35b-a3... Conversational Endpoints compatible Image-text-to-text Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/sweagent/selfrl-fullfiles-i49

Selfrl Fullfiles I49 Parameters and Internals

LLM Name	Selfrl Fullfiles I49
Repository 🤗	https://huggingface.co/sweagent/selfrl-fullfiles-i49
Base Model(s)	Qwen/Qwen3.5-35B-A3B-Base Qwen/Qwen3.5-35B-A3B-Base
Model Size	35b
Required VRAM	137.1 GB
Updated	2026-09-15
Maintainer	sweagent
Model Type	qwen3_5_moe
Model Files	5.4 GB: 0-of-26 5.4 GB: 1-of-26 5.4 GB: 2-of-26 5.4 GB: 3-of-26 5.4 GB: 4-of-26 5.4 GB: 5-of-26 5.4 GB: 6-of-26 5.4 GB: 7-of-26 5.4 GB: 8-of-26 5.4 GB: 9-of-26 5.4 GB: 10-of-26 5.4 GB: 11-of-26 4.9 GB: 12-of-26 5.4 GB: 13-of-26 5.4 GB: 14-of-26 5.4 GB: 15-of-26 5.4 GB: 16-of-26 5.4 GB: 17-of-26 5.4 GB: 18-of-26 5.4 GB: 19-of-26 5.4 GB: 20-of-26 5.4 GB: 21-of-26 5.4 GB: 22-of-26 5.4 GB: 23-of-26 5.4 GB: 24-of-26 2.6 GB: 25-of-26
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Selfrl Fullfiles I49 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 Selfrl Fullfiles I49

Best Alternatives	Context / RAM	Downloads	Likes
Ornith 1.5 35B A3B NPU2	256K / GB	213	1
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Ornith 1.0 35B	0K / 70.4 GB	2257785	505
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343
KAT Coder V2.5 Dev	0K / 69.7 GB	17885	537
Qwen AgentWorld 35B A3B	0K / 69.2 GB	66155	665
Qwen3.6 35B A3B NVFP4 Fast	0K / 23.6 GB	463661	98
Ornith 1.0 35B FP8	0K / 37.4 GB	852240	81

Note: green Score (e.g. "73.2") means that the model is better than sweagent/selfrl-fullfiles-i49.