Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor

amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor

Text Generation15.1B parameterstransformersLicense: other

Tracked by OpenModelStats since September 22, 2026View on Hugging Face ↗

Downloads 30D: 195
Total downloads: 195
Gained 7D: —
Gained 30D: —
Likes: 2
Rank · tracked models: —; –this week
Parameters: 15.1B
Last source update: Sep 22, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-22. Charts appear as daily observations accumulate.

Overview

Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor is a text generation model published by amd. OpenModelStats has tracked the model since Sep 22, 2026, most recently observing it Oct 2, 2026.

Published: Sep 22, 2026
Last updated: Sep 22, 2026
Library: transformers
License: other
Task: Text Generation
Parameters: 15,058,031,536
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorsdeepseek_v3text-generationquantizedint4w4a16weight-only4-bitllm-compressorzendnncompressed-tensors

Publisher

amdView publisher statistics →

Derived from amd/Instella-MoE-16B-A3B-SFT (reported by the source; parent not yet tracked).

Similar models

Models similar to Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor
Model	Task	DL 30D	Likes	Params
bigyi-15babacusai	Text Generation	8,672	11	15.1B
phi-4-unsloth-bnb-4bitunsloth	Text Generation	4,476	65	15.1B
granite-4.2-30b-NVFP4vcruz305	Text Generation	502	1	15B
Phi-4-reasoning-plus-unsloth-bnb-4bitunsloth	Text Generation	173	4	15.1B
phi-4-bnb-4bitunsloth	Text Generation	1,074	17	15.1B
DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bitunsloth	Text Generation	3,374	30	15.1B