LLM EXPLORER 60,062 MODELS INDEXED

Qwen3.8 Flash Next OQ4e 100K MTP by jedisct1

By jedisct1 · 380 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next OQ4e 100K MTP is an open-source language model by jedisct1. Features: 31.4b LLM, VRAM: 108.9GB, License: other, LLM Explorer Score: 0.33.

  4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Image-text-to-text   Mlx   Mtp   Omlx   Qwen4   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow   Tool-calling   Vision
Model Card on HF 🤗: https://huggingface.co/jedisct1/Qwen3.8-Flash-Next-oQ4e-100K-MTP 

Qwen3.8 Flash Next OQ4e 100K MTP Parameters and Internals

LLM NameQwen3.8 Flash Next OQ4e 100K MTP
Repository 🤗https://huggingface.co/jedisct1/Qwen3.8-Flash-Next-oQ4e-100K-MTP 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size31.4b
Required VRAM108.9 GB
Updated2026-08-31
Maintainerjedisct1
Model Typeqwen4_exp
Model Files  5.0 GB: 1-of-22   5.0 GB: 2-of-22   5.0 GB: 3-of-22   5.0 GB: 4-of-22   5.0 GB: 5-of-22   5.0 GB: 6-of-22   5.0 GB: 7-of-22   5.5 GB: 8-of-22   5.1 GB: 9-of-22   5.2 GB: 10-of-22   5.2 GB: 11-of-22   5.2 GB: 12-of-22   5.2 GB: 13-of-22   5.2 GB: 14-of-22   5.2 GB: 15-of-22   5.2 GB: 16-of-22   5.2 GB: 17-of-22   5.2 GB: 18-of-22   5.2 GB: 19-of-22   5.2 GB: 20-of-22   5.2 GB: 21-of-22   0.9 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 OQ4e 100K MTP

Best Alternatives
Context / RAM
Downloads
Likes
... Next Uncensored OQ4e 100K MTP0K / 108.9 GB9572
Note: green Score (e.g. "73.2") means that the model is better than jedisct1/Qwen3.8-Flash-Next-oQ4e-100K-MTP.