gpt-oss-20b-TurboQuant-MLX-4bit

majentik/gpt-oss-20b-TurboQuant-MLX-4bit

Text Generation3.9B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
475
Total downloads
2,158
Gained 7D
Gained 30D
Likes
2
Rank · tracked models
#28,129
this week
Parameters
3.9B
Last source update
Aug 20, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Likes over time

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Overview

gpt-oss-20b-TurboQuant-MLX-4bit is a text generation model published by majentik. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 2h ago.

Published
Apr 14, 2026
Last updated
Aug 20, 2026
Library
mlx
License
apache-2.0
Task
Text Generation
Parameters
3,871,285,824
Spaces
Derivative models
Velocity 7D/day
mlxsafetensorsgpt_ossturboquantkv-cache-quantizationgpt-ossopenaimoequantized4bittext-generationconversational

Publisher

majentikView publisher statistics →

Derived from openai/gpt-oss-20b (reported by the source; parent not yet tracked).

Similar models

Models similar to gpt-oss-20b-TurboQuant-MLX-4bit
ModelDL 30D
typhoon2.1-gemma3-4btyphoon-ai1,308
Nile-Chat-4BMBZUAI-Paris1,293
Phi-4-mini-flash-reasoningmicrosoft885
Koa-AI-v1-Code-3Bvamazing2,168
Ministral-3-3B-Instruct-2512-roleplay-tuned-ERP-tolerantIndexnusrefather1,827
Phi-4-mini-instructmicrosoft489.7K