Quantized text-to-image diffusion models (FP8 / GGUF). Transformer (DiT) quantized; VAE & text encoders from originals. By axteam.
WINSTECHNET_AX
community
AI & ML interests
None defined yet.
Recent Activity
Quantized OCR / document VLMs (GLM-OCR, PaddleOCR-VL) — compressed-tensors + GGUF for vLLM / llama.cpp. By axteam.
axteam's Gemma 4 quantizations — FP8 dynamic, AWQ INT4/INT8, NVFP4 (W4A4 & W4A16), and GGUF — for 12B-it, E4B-it, 26B-A4B(+it), 31B(+it).
-
axteam/gemma-4-12B-it-FP8-dynamic
Image-Text-to-Text • 12B • Updated • 63 • 3 -
axteam/gemma-4-12B-it-AWQ-8bit
Image-Text-to-Text • 12B • Updated • 52 • 3 -
axteam/gemma-4-12B-it-AWQ-4bit
Image-Text-to-Text • 12B • Updated • 231 • 2 -
axteam/gemma-4-12B-it-NVFP4A16
Image-Text-to-Text • 12B • Updated • 57 • 1
-
WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
Text Generation • 8B • Updated • 1.75k • • 81 -
athena129/CyberSecQwen-4B
Text Generation • 4B • Updated • 188 • 14 -
Trendyol/Trendyol-Cybersecurity-LLM-Qwen3-32B-Q8_0-GGUF
33B • Updated • 278 • 76 -
IMPERUM/Imperum-CybersecurityLLM-v1.0-GGUF
Text Generation • 35B • Updated • 3.64k • 26
Quantized text-to-image diffusion models (FP8 / GGUF). Transformer (DiT) quantized; VAE & text encoders from originals. By axteam.
Quantized OCR / document VLMs (GLM-OCR, PaddleOCR-VL) — compressed-tensors + GGUF for vLLM / llama.cpp. By axteam.
axteam's Gemma 4 quantizations — FP8 dynamic, AWQ INT4/INT8, NVFP4 (W4A4 & W4A16), and GGUF — for 12B-it, E4B-it, 26B-A4B(+it), 31B(+it).
-
axteam/gemma-4-12B-it-FP8-dynamic
Image-Text-to-Text • 12B • Updated • 63 • 3 -
axteam/gemma-4-12B-it-AWQ-8bit
Image-Text-to-Text • 12B • Updated • 52 • 3 -
axteam/gemma-4-12B-it-AWQ-4bit
Image-Text-to-Text • 12B • Updated • 231 • 2 -
axteam/gemma-4-12B-it-NVFP4A16
Image-Text-to-Text • 12B • Updated • 57 • 1
-
WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
Text Generation • 8B • Updated • 1.75k • • 81 -
athena129/CyberSecQwen-4B
Text Generation • 4B • Updated • 188 • 14 -
Trendyol/Trendyol-Cybersecurity-LLM-Qwen3-32B-Q8_0-GGUF
33B • Updated • 278 • 76 -
IMPERUM/Imperum-CybersecurityLLM-v1.0-GGUF
Text Generation • 35B • Updated • 3.64k • 26