LLM EXPLORER 60,519 MODELS INDEXED

Qwen3.8 Flash Next Int2 Mixed AutoRound 24GB SGLang by HaberstrohSystems

By HaberstrohSystems · 122 downloads

Qwen3.8 Flash Next Int2 Mixed AutoRound 24GB SGLang is an open-source language model by HaberstrohSystems. Features: 10.9b LLM, VRAM: 36.9GB, License: other, LLM Explorer Score: 0.32.

  2-bit   24gb   Auto-round Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Blackwell   Conversational   Dataset:neelnanda/pile-10k   Int2   Long-context   Mixed-precision   Moe   Qwen   Qwen4 exp   Region:us   Safetensors   Sglang   Sharded   Tensorflow   Text-only

Qwen3.8 Flash Next Int2 Mixed AutoRound 24GB SGLang Parameters and Internals

LLM NameQwen3.8 Flash Next Int2 Mixed AutoRound 24GB SGLang
Repository πŸ€—https://huggingface.co/HaberstrohSystems/Qwen3.8-Flash-Next-int2-mixed-AutoRound-24GB-SGLang 
Base Model(s)  Qwen/Qwen3.8-Flash-Next-FP8   Qwen/Qwen3.8-Flash-Next-FP8
Model Size10.9b
Required VRAM36.9 GB
Updated2026-09-05
MaintainerHaberstrohSystems
Model Typeqwen4_exp
Model Files  5.1 GB: 1-of-8   5.0 GB: 2-of-8   5.0 GB: 3-of-8   5.0 GB: 4-of-8   5.1 GB: 5-of-8   5.0 GB: 6-of-8   5.0 GB: 7-of-8   1.7 GB: 8-of-8   1.8 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.16.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace