HarshBhanushali7705/medgemma-27b-text-it-GPTQ-4bit
Text Generation • 27B • Updated • 467 • 4
GPTQ
GPTQ is a fast, accurate post-training quantization method for LLMs. It compresses 16-bit model weights down to 4-bit integers.
-
-
DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B
Text Generation • 18B • Updated • 165 • 26 -
DavidAU/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x
Text Generation • 6B • Updated • 65 • 6 -
DavidAU/Qwen3-Zero-Coder-Reasoning-0.8B
Text Generation • 0.8B • Updated • 131 • 5 -
DavidAU/Qwen3-Blitzar-Coder-F1-6B-Brainstorm20x
Text Generation • 6B • Updated • 249 • 9 -
DavidAU/Qwen3-Jan-Nano-128k-6B-Brainstorm20x
Text Generation • 6B • Updated • 136 • 6 -
DavidAU/Qwen3-53B-A3B-2507-TOTAL-RECALL-v2-MASTER-CODER
Text Generation • 53B • Updated • 117 • 16 -
DavidAU/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER
Text Generation • 53B • Updated • 146 • 13 -
DavidAU/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-1million-ctx
Text Generation • 42B • Updated • 163 • 9 -
DavidAU/Qwen3-Coder-53B-A3B-Instruct-TOTAL-RECALL-v2-MASTER-CODER-L
Text Generation • 53B • Updated • 258 • 20 -
DavidAU/L3-Dark-Planet-8B
Text Generation • 8B • Updated • 141 • 10 -
DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B
Text Generation • 8B • Updated • 187 • 10 -
DavidAU/Mistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B
Text Generation • 24B • Updated • 71 • 5 -
DavidAU/Qwen3-30B-A1.5B-High-Speed
Text Generation • 31B • Updated • 104 • 13 -
DavidAU/Qwen3-8B-64k-Context-2X-Josiefied-Uncensored
Text Generation • 8B • Updated • 551 • 18