LLM EXPLORER 65,695 MODELS INDEXED

Qwen3.8 Flash Next OpenSeek EXL3 by LichAmnesia

By LichAmnesia · 58 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next OpenSeek EXL3 is an open-source language model by LichAmnesia. Features: 89.7b LLM, VRAM: 128.3GB, License: other.

  4-bit Base model:merge:nvidia/qwen3.... Base model:merge:wrldsuksgo2ma... Base model:nvidia/qwen3.8-flas... Base model:wrldsuksgo2mars/qwe...   Blackwell   Conversational   Exl3   Fp8   Image-text-to-text   Openseek-recipe   Quantized   Qwen   Qwen4 exp   Region:us   Rtx-pro-6000   Safetensors   Sharded   Tensorflow   Tool-calling   Vllm
Model Card on HF 🤗: https://huggingface.co/LichAmnesia/Qwen3.8-Flash-Next-OpenSeek-EXL3 

Qwen3.8 Flash Next OpenSeek EXL3 Parameters and Internals

LLM NameQwen3.8 Flash Next OpenSeek EXL3
Repository 🤗https://huggingface.co/LichAmnesia/Qwen3.8-Flash-Next-OpenSeek-EXL3 
Base Model(s)  wrldsuksgo2mars/Qwen3.8-Flash-Next-EXL3-K4.25-v1   nvidia/Qwen3.8-Flash-Next-NVFP4   wrldsuksgo2mars/Qwen3.8-Flash-Next-EXL3-K4.25-v1   nvidia/Qwen3.8-Flash-Next-NVFP4
Model Size89.7b
Required VRAM128.3 GB
Updated2026-10-27
MaintainerLichAmnesia
Model Typeqwen4_exp
Model Files  6.8 GB: 1-of-22   4.0 GB: 2-of-22   4.0 GB: 3-of-22   4.0 GB: 4-of-22   4.0 GB: 5-of-22   4.0 GB: 6-of-22   4.0 GB: 7-of-22   4.0 GB: 8-of-22   4.0 GB: 9-of-22   4.0 GB: 10-of-22   4.0 GB: 11-of-22   4.0 GB: 12-of-22   4.0 GB: 13-of-22   6.6 GB: 14-of-22   8.6 GB: 15-of-22   8.6 GB: 16-of-22   8.6 GB: 17-of-22   8.6 GB: 18-of-22   8.6 GB: 19-of-22   8.6 GB: 20-of-22   8.6 GB: 21-of-22   6.7 GB: 22-of-22
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 Flash Next OpenSeek EXL3

Best Alternatives
Context / RAM
Downloads
Likes
...en3.8 Flash Next EXL3 K4.25 V10K / 179.5 GB1522
Note: green Score (e.g. "73.2") means that the model is better than LichAmnesia/Qwen3.8-Flash-Next-OpenSeek-EXL3.