LLM EXPLORER 67,078 MODELS INDEXED

Qwen3.5 9B Brainwaves DeepThought STEM OneJev1.6 Q8 Hi Mlx by nightmedia

By nightmedia · 53 downloads
HF Repo ↗ Copy URL

Qwen3.5 9B Brainwaves DeepThought STEM OneJev1.6 Q8 Hi Mlx is an open-source language model by nightmedia. Features: 9b LLM, VRAM: 10.9GB, License: apache-2.0, Quantized, Code Generating, LLM Explorer Score: 0.3.

  1m context   256k context   8-bit   All genres Base model:merge:nightmedia/qw... Base model:merge:omnijev/oneje... Base model:merge:xtools-at/qwe... Base model:nightmedia/qwen3.5-... Base model:omnijev/onejev1.6-9... Base model:xtools-at/qwen3.5-9...   Bf16   Chain-of-thought   Claude   Codegen   Coder-flash   Coding   Conversational   Creative   Creative writing   Deckard(qx)   Distillation   En   Endpoints compatible   Es   Experimental   Fiction   Fiction story   Fiction writing   Image-text-to-text   Ja   Long-cot   Math   Merge   Mergekit   Multi-token-prediction   Multilingual   Plot generation   Polaris   Polaris-alpha   Q8   Quantized   Qwen3.5   Qwen3 5   Reasoning   Region:us   Research   Roleplaying   Safetensors   Scene continue   Science fiction   Sharded   Speculative-decoding   Stem   Story   Story generation   Storytelling   Sub-plot generation   Tensorflow   Vivid prosing   Vivid writing   Writing   Zh
Model Card on HF 🤗: https://huggingface.co/nightmedia/Qwen3.5-9B-Brainwaves-DeepThought-STEM-OneJev1.6-q8-hi-mlx 

Qwen3.5 9B Brainwaves DeepThought STEM OneJev1.6 Q8 Hi Mlx Parameters and Internals

LLM NameQwen3.5 9B Brainwaves DeepThought STEM OneJev1.6 Q8 Hi Mlx
Repository 🤗https://huggingface.co/nightmedia/Qwen3.5-9B-Brainwaves-DeepThought-STEM-OneJev1.6-q8-hi-mlx 
Model Nameunsloth/Qwen3.5-9B
Base Model(s)  OmniJev/OneJev1.6-9B   xtools-at/Qwen3.5-9B-DeepThought-STEM   nightmedia/Qwen3.5-9B-Brainwaves   OmniJev/OneJev1.6-9B   xtools-at/Qwen3.5-9B-DeepThought-STEM   nightmedia/Qwen3.5-9B-Brainwaves
Model Size9b
Required VRAM10.9 GB
Updated2026-11-10
Maintainernightmedia
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-3   4.5 GB: 2-of-3   1.1 GB: 3-of-3
Supported Languagesen zh ja es
Quantization Typeq8
Generates CodeYes
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.22.1
Tokenizer ClassQwen3_5Tokenizer
Padding Token<|vision_pad|>
Errorsreplace

Best Alternatives to Qwen3.5 9B Brainwaves DeepThought STEM OneJev1.6 Q8 Hi Mlx

Best Alternatives
Context / RAM
Downloads
Likes
...ves DeepThought STEM OneJev1.60K / 18.9 GB304
...r Flash Heretic GPTQPro W4 G640K / 9.3 GB471
...opus3.5 9B Coder Flash Heretic0K / 18.8 GB471
Qwopus3 5 9B Coder Flash0K / 19.3 GB37210
Prism Coder 9B0K / 19.3 GB1894
Qwen3.5 9B DS9 USS Defiant0K / 19.2 GB503
Note: green Score (e.g. "73.2") means that the model is better than nightmedia/Qwen3.5-9B-Brainwaves-DeepThought-STEM-OneJev1.6-q8-hi-mlx.