LLM EXPLORER 67,808 MODELS INDEXED

Qwen3 8B DFlash B16 RTN INT8 Safetensors by simaai

By simaai · 65 downloads

Qwen3 8B DFlash B16 RTN INT8 Safetensors is an open-source language model by simaai. Features: 8b LLM, VRAM: 1.1GB, Context: 40K, License: mit, LLM Explorer Score: 0.25.

Base model:quantized:z-lab/qwe... Base model:z-lab/qwen3-8b-dfla...   Compressed-tensors   Custom code   Dflash   Int8   Qwen3   Region:us   Rtn   Safetensors   Simaai   Speculative-decoding

Qwen3 8B DFlash B16 RTN INT8 Safetensors Parameters and Internals

LLM NameQwen3 8B DFlash B16 RTN INT8 Safetensors
Repository πŸ€—https://huggingface.co/simaai/Qwen3-8B-DFlash-b16-RTN-INT8-Safetensors 
Base Model(s)  Qwen3 8B DFlash B16   z-lab/Qwen3-8B-DFlash-b16
Model Size8b
Required VRAM1.1 GB
Updated2026-10-16
Maintainersimaai
Model Typeqwen3
Model Files  1.1 GB
Model ArchitectureDFlashDraftModel
Licensemit
Context Length40960
Model Max Length40960
Transformers Version4.57.3
Vocabulary Size151936

Best Alternatives to Qwen3 8B DFlash B16 RTN INT8 Safetensors

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 8B DFlash B1640K / 2.1 GB9603228
...1 8B Instruct DFlash UltraChat40K / 2.1 GB231764
...8B Instruct DFlash Safetensors40K / 1.1 GB2350
...wallow 8B Instruct V0.5 DFlash0K / 2.1 GB400
Note: green Score (e.g. "73.2") means that the model is better than simaai/Qwen3-8B-DFlash-b16-RTN-INT8-Safetensors.