Qwen3-8B-DFlash-FP8-BLOCK

inference-optimization/Qwen3-8B-DFlash-FP8-BLOCK

Text Generation2.3B parametersspeculatorsLicense: apache-2.0

Tracked by OpenModelStats since September 28, 2026View on Hugging Face ↗

Downloads 30D: 17
Total downloads: 17
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: —; –this week
Parameters: 2.3B
Last source update: Sep 28, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-28. Charts appear as daily observations accumulate.

Overview

Qwen3-8B-DFlash-FP8-BLOCK is a text generation model published by inference-optimization. OpenModelStats has tracked the model since Sep 28, 2026, most recently observing it Sep 29, 2026.

Published: Sep 28, 2026
Last updated: Sep 28, 2026
Library: speculators
License: apache-2.0
Task: Text Generation
Parameters: 2,293,286,144
Spaces: —
Derivative models: —
Velocity 7D/day: —

speculatorssafetensorsspeculative-decodingdflashqwen3quantizedfp8block-quantizationdata-freetext-generationcustom_codebase_model:Qwen/Qwen3-8B

Publisher

inference-optimizationView publisher statistics →

Derived from Qwen/Qwen3-8B (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-8B-DFlash-FP8-BLOCK
Model	Task	DL 30D	Likes	Params
Qwen3.5-4B-Mtrymirai	Text Generation	403	2	2.3B
Midm-2.0-Mini-InstructK-intelligence	Text Generation	24.2K	62	2.3B
GLM-5.3-NVFP4-DFlashmodal-labs	Text Generation	2,253	2	2.3B
Qwen3.8-2B-Distillempero-ai	Text Generation	5,951	46	2.3B
Qwen3.5-2B-Opus-Distilreaperdoesntknow	Text Generation	5,104	1	2.3B
Qwen3.5-2B-CyberSecreaperdoesntknow	Text Generation	5,047	0	2.3B