What are the hardware requirements for Affine 5dfqbbh8ev Sft?

Affine 5dfqbbh8ev Sft requires approximately 69.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Affine 5dfqbbh8ev Sft and how large is it?

Affine 5dfqbbh8ev Sft is developed by kevin954, a model with 34.7b 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 Affine 5dfqbbh8ev Sft?

Affine 5dfqbbh8ev Sft is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Affine 5dfqbbh8ev Sft by kevin954 — VRAM 69.3GB

Name: Affine 5dfqbbh8ev Sft
Author: kevin954

Affine 5dfqbbh8ev Sft is an open-source language model by kevin954. Features: 34.7b LLM, VRAM: 69.3GB.

Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/kevin954/Affine-5dfqbbh8ev-sft

Affine 5dfqbbh8ev Sft Parameters and Internals

LLM Name	Affine 5dfqbbh8ev Sft
Repository 🤗	https://huggingface.co/kevin954/Affine-5dfqbbh8ev-sft
Model Size	34.7b
Required VRAM	69.3 GB
Updated	2026-08-09
Maintainer	kevin954
Model Type	qwen3_5_moe
Model Files	49.7 GB: 1-of-2 19.6 GB: 2-of-2 2.6 GB
Model Architecture	Qwen3_5MoeForConditionalGeneration
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Affine 5dfqbbh8ev Sft 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 Affine 5dfqbbh8ev Sft

Best Alternatives	Context / RAM	Downloads	Likes
5eqdtdzqle Ckpt1000 M7	0K / 71.7 GB	22	0
Agents A1 OptiQ 4bit	0K / 22.2 GB	891	3
...CybersecurityLLM V1.0 Mlx 4Bit	0K / 19.5 GB	773	45
KAT Coder V2.5 Dev OptiQ 4bit	0K / 21.9 GB	114	3
XYZ Aquila Mini OptiQ 4bit	0K / 36.3 GB	34	3

Note: green Score (e.g. "73.2") means that the model is better than kevin954/Affine-5dfqbbh8ev-sft.