Qwen3-Next-80B-A3B-Instruct-quantized.w4a16
— Model Architecture: Qwen3NextForCausalLM — Input: Text — Output: Text — Model Optimizations: — Weight quantization: INT4 —...
Метка: quantized
Qwen3-30B-A3B-Instruct-2507-unsloth-MagicQuant-Hybrid-GGUF
(DEPRECIATED — Part of MagicQuant v1.0 which had significant flaws. Please utilize v2.0 which is production ready) >...
MiroThinker-v1.0-30B-FP8
This is an FP8 quantized version of miromind-ai/MiroThinker-v1.0-30B, created using llmcompressor (Neural Magic). Key Benefits: — ~50% smaller...
Ministral-3-3B-Reasoning-2512-GGUF
— Model creator: mistralai — Original model: mistralai/Ministral-3-3B-Reasoning-2512 MaziyarPanahi/Ministral-3-3B-Reasoning-2512-GGUF contains GGUF format model files for mistralai/Ministral-3-3B-Reasoning-2512. GGUF is...
NVIDIA-Nemotron-Nano-12B-v2-GGUF
— Model creator: nvidia — Original model: nvidia/NVIDIA-Nemotron-Nano-12B-v2 MaziyarPanahi/NVIDIA-Nemotron-Nano-12B-v2-GGUF contains GGUF format model files for nvidia/NVIDIA-Nemotron-Nano-12B-v2. GGUF is...
CaptureTheFlag-CypherMindLLM-XRLAB-GGUF
CypherMind — это широкоязычная модель, специально настроенная для задач захвата флага (CTF) и кибербезопасности. Он помогает в решении...
Qwen3-VL-235B-A22B-Instruct-FP8-dynamic
— Model Architecture: Qwen3VLMoeForConditionalGeneration — Input: Text/Image/Video — Output: Text — Model Optimizations: — Weight quantization: FP8 —...
Qwen3-1.7B-f16
Это GGUF-количественная версия языковой модели Qwen/Qwen3-1.7B — сбалансированный LLM с 1,7 миллиардами параметров, предназначенный для эффективного локального вывода...
Devstral-Small-2507-FP8-Dynamic
— Model Architecture: MistralForCausalLM — Input: Text — Output: Text — Model Optimizations: — Activation quantization: FP8 —...
Qwen3-30B-A3B-Instruct-2507-GGUF
— Model creator: Qwen — Original model: Qwen/Qwen3-30B-A3B-Instruct-2507 MaziyarPanahi/Qwen3-30B-A3B-Instruct-2507-GGUF contains GGUF format model files for Qwen/Qwen3-30B-A3B-Instruct-2507. GGUF is...