deepseek-ai/DeepSeek-V4.1-Flash-1017
Image-Text-to-Text • 763B • Updated • 349k • • 5.53k
🤝 Open to Collab
Paris Michalas
Paris99
AI & ML interests
Partner at NetProjects (Internet Projects Ltd). Running decision models and local LLMs on Apple Silicon with MLX: calibrated one-pass judges, claim-vs-evidence checking, second-opinion routing and faster speculative decoding. My MLX ports under netprojects include AutoTrust-JEV 35B & 27B, Granite Switch 4.1, Nemotron 3.5 Embed & Rerank, Nemotron Dory, GLiDE, H2O Lightning, SenseNova Loop, Cosmos3-Edge & Omni, and the Tencent DSpine drafter for Qwen3.8-27B. See the My MLX ports collection.
Recent Activity
new activity about 17 hours ago
JuneoAI/Laplace-1-Atlas:MLX and GGUF builds (MLX 8/6/4-bit + bf16, GGUF Q8_0/Q6_K/Q4_K_M) new activity about 17 hours ago
netprojects/README:Mention GGUF, sort models by downloads, list bf16/8-bit first new activity about 17 hours ago
netprojects/README:Link GGUF collection, mention llama.cpp, order code by popularityOrganizations
liked 2
models 23 days ago
liked 4
models 24 days ago
nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16
Text Generation • 4B • Updated • 13.9k • 254
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Text Generation • 32B • Updated • 1.04M • • 272
autotrust/AutoTrust-Decider-Pro-35B
Text Classification • 36B • Updated • 1.65M • 3.11k
h2oai/h2o-lightning-4b
Image-Text-to-Text • 5B • Updated • 11k • 107
liked a
model about 1 month ago