LLM EXPLORER 60,220 MODELS INDEXED

Qwen3.8 Flash Next W4A16 PLE4 MTP Spark by edougawa

By edougawa · 39 downloads

Qwen3.8 Flash Next W4A16 PLE4 MTP Spark is an open-source language model by edougawa. Features: 135.2b LLM, VRAM: 0.1GB, License: other, LLM Explorer Score: 0.3.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Compressed-tensors   Conversational   Dgx-spark   Endpoints compatible   Gb10   Image-text-to-text   Int4   Mtp   Multimodal   Quantized   Qwen   Qwen3.8   Qwen4-exp   Qwen4 exp   Region:us   Safetensors   Speculative-decoding   Vision   Vision-language   W4a16

Qwen3.8 Flash Next W4A16 PLE4 MTP Spark Parameters and Internals

LLM NameQwen3.8 Flash Next W4A16 PLE4 MTP Spark
Repository πŸ€—https://huggingface.co/edougawa/Qwen3.8-Flash-Next-W4A16-PLE4-MTP-Spark 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size135.2b
Required VRAM0.1 GB
Updated2026-09-02
Maintaineredougawa
Model Typeqwen4_exp
Model Files  4.0 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.6 GB   1.3 GB   6.3 GB   6.7 GB   2.7 GB   4.4 GB   6.3 GB   6.7 GB   5.9 GB   6.2 GB   5.9 GB   6.3 GB   7.1 GB   0.3 GB   0.1 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace