ComfyUI Node: ๐ค Nexa Text Generation
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
๐ค GGUF-Fusion/Nexa
Inputs
model_config NEXA_MODEL
preset_model
- Custom (่พๅ ฅ่ชๅฎไนๆจกๅ ID)
- --- Preset Models (้่ฆ nexa pull) ---
- DavidAU/Qwen3-8B-64k-Josiefied-Uncensored-HORROR-Max-GGUF:Q6_K
- mradermacher/Huihui-Qwen3-4B-Thinking-2507-abliterated-GGUF:Q8_0
- prithivMLmods/Qwen3-4B-2507-abliterated-GGUF:Q8_0
- mradermacher/Qwen3-4B-Thinking-2507-Uncensored-Fixed-GGUF:Q8_0
- mradermacher/Qwen3-Short-Story-Instruct-Uncensored-262K-ctx-4B-GGUF:Q8_0
custom_model STRING
auto_download BOOLEAN
max_tokens INT
temperature FLOAT
top_p FLOAT
top_k INT
repetition_penalty FLOAT
enable_thinking BOOLEAN
prompt STRING
Outputs
STRING
STRING
Extension: ComfyUI-GGUF-FX
ComfyUI nodes for running GGUF quantized Qwen2.5-VL models using llama.cpp
Authored by weekii
Looking for a different node?
More nodes in ComfyUI-GGUF-FX
- ๐ง GGUF Model Manager
- ๐ฅ๏ธ Local Text Model Loader
- ๐ค Multi-Image Analysis
- ๐ค Multi-Image Comparison
- ๐ค Nexa Model Selector
- ๐ค Nexa Service Status
- ๐ Remote Text Model Selector
- ๐ค System Prompt Config
- ๐ค Text Generation
- ๐ค Vision Language Generation
- ๐ค Vision Language (Transformers)
- ๐ค Vision Model Loader
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.