TokForge-ready on-device image generation bundles, including Bonsai/FLUX/sd.cpp assets staged for Android CPU/OpenCL lab and release testing.
Ivan M
darkmaniac7
AI & ML interests
None yet
Recent Activity
updated a collection 1 day ago
TokForge Image Generation Models updated a model 1 day ago
darkmaniac7/TokForge-Bonsai-Image-4B-GGUF published a model 1 day ago
darkmaniac7/TokForge-Bonsai-Image-4B-GGUFOrganizations
None yet
Top open-source models in MNN Q4 for TokForge mobile inference. Google, Meta, Mistral, DeepSeek, HuggingFace.
Uncensored Qwen3/3.5 models in MNN Q4 format for TokForge mobile inference. Josiefied, Heretic, and Claude variants.
-
darkmaniac7/Josiefied-Qwen3.5-0.8B-gabliterated-v1-MNN
Text Generation • Updated • 23 • 2 -
darkmaniac7/Josiefied-Qwen3-4B-abliterated-v2-MNN
Text Generation • Updated • 13 -
darkmaniac7/Josiefied-Qwen3-8B-abliterated-v1-MNN
Text Generation • Updated • 4 • 1 -
darkmaniac7/Josiefied-Qwen3-14B-abliterated-v3-MNN
Text Generation • Updated • 8
Google Gemma 4 models (E2B, E4B) in MNN Q4 format for TokForge mobile inference. Requires TokForge 3.4.9+.
Uncensored Llama/Dolphin/Mistral models in MNN Q4 for TokForge mobile inference.
-
darkmaniac7/Panth-L3-Blackroot-Nephra-8B-MNN
Text Generation • Updated • 3 -
darkmaniac7/Dolphin3.0-Llama3.1-8B-MNN
Text Generation • Updated • 1 • 1 -
darkmaniac7/Meta-Llama-3.1-8B-Instruct-abliterated-MNN
Text Generation • Updated • 2 -
darkmaniac7/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-MNN
Text Generation • Updated • 3
Small MNN draft models and speculative-decoding bundles for TokForge on Android. Includes practical Qwen3 0.6B drafts plus experimental variants.
TokForge-ready on-device image generation bundles, including Bonsai/FLUX/sd.cpp assets staged for Android CPU/OpenCL lab and release testing.
Google Gemma 4 models (E2B, E4B) in MNN Q4 format for TokForge mobile inference. Requires TokForge 3.4.9+.
Top open-source models in MNN Q4 for TokForge mobile inference. Google, Meta, Mistral, DeepSeek, HuggingFace.
Uncensored Llama/Dolphin/Mistral models in MNN Q4 for TokForge mobile inference.
-
darkmaniac7/Panth-L3-Blackroot-Nephra-8B-MNN
Text Generation • Updated • 3 -
darkmaniac7/Dolphin3.0-Llama3.1-8B-MNN
Text Generation • Updated • 1 • 1 -
darkmaniac7/Meta-Llama-3.1-8B-Instruct-abliterated-MNN
Text Generation • Updated • 2 -
darkmaniac7/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-MNN
Text Generation • Updated • 3
Uncensored Qwen3/3.5 models in MNN Q4 format for TokForge mobile inference. Josiefied, Heretic, and Claude variants.
-
darkmaniac7/Josiefied-Qwen3.5-0.8B-gabliterated-v1-MNN
Text Generation • Updated • 23 • 2 -
darkmaniac7/Josiefied-Qwen3-4B-abliterated-v2-MNN
Text Generation • Updated • 13 -
darkmaniac7/Josiefied-Qwen3-8B-abliterated-v1-MNN
Text Generation • Updated • 4 • 1 -
darkmaniac7/Josiefied-Qwen3-14B-abliterated-v3-MNN
Text Generation • Updated • 8
Small MNN draft models and speculative-decoding bundles for TokForge on Android. Includes practical Qwen3 0.6B drafts plus experimental variants.