{"id":1333,"date":"2026-09-17T17:03:05","date_gmt":"2026-09-17T08:03:05","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/model-nex-agi-nex-n2-5-mini-en\/"},"modified":"2026-09-19T06:50:54","modified_gmt":"2026-09-18T21:50:54","slug":"model-nex-agi-nex-n2-5-mini-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-nex-agi-nex-n2-5-mini-en\/","title":{"rendered":"nex-agi\/Nex-N2.5-mini: Models, Variants and Hardware Requirements"},"content":{"rendered":"

Everything Local Model Watch has published about the nex-agi\/Nex-N2.5-mini<\/strong> family: 2 article(s) covering the base model and its fine-tunes, plus converted builds we tracked after publication. Memory requirements below are computed by this site from file sizes, not quoted from model cards. Part of our model family index<\/a>.<\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Family<\/td>\nnex-agi\/Nex-N2.5-mini<\/a><\/td>\n<\/tr>\n
Publisher<\/td>\nnex-agi<\/td>\n<\/tr>\n
Parameters<\/td>\n35.1B<\/td>\n<\/tr>\n
License (model card)<\/td>\napache-2.0<\/td>\n<\/tr>\n
Smallest VRAM tier<\/td>\n16GB<\/td>\n<\/tr>\n
Articles<\/td>\n2<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Hardware Requirements<\/h2>\n

Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 35.1B parameters<\/p>\n

\n\n\n\n\n\n\n\n\n\n
Your VRAM<\/th>\nQuantization<\/th>\nFile size<\/th>\nEst. memory needed<\/th>\n<\/tr>\n<\/thead>\n
16GB (RTX 5060 Ti 16GB \/ 4060 Ti 16GB, etc.)<\/td>\nQ2_K<\/td>\n12.9GB<\/td>\n15.5GB<\/td>\n<\/tr>\n
24GB (RTX 4090 \/ 3090, etc.)<\/td>\nQ4_K_S<\/td>\n19.5GB<\/td>\n23.4GB<\/td>\n<\/tr>\n
32GB (RTX 5090, etc.)<\/td>\nQ5_K_M<\/td>\n25.1GB<\/td>\n30.2GB<\/td>\n<\/tr>\n
48GB (RTX 6000 Ada \/ A6000, etc.)<\/td>\nQ8_0<\/td>\n34.4GB<\/td>\n41.3GB<\/td>\n<\/tr>\n
80GB class (A100 \/ H100)<\/td>\nBF16<\/td>\n64.6GB<\/td>\n77.5GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model’s authors. File sizes are measured from the converted build bartowski\/nex-agi_Nex-N2.5-mini-GGUF<\/a>. Compare with other models in our VRAM quick reference<\/a>. What the quantization names mean: glossary<\/a>.<\/em><\/p>\n

Quantized and Converted Variants<\/h2>\n
\n

\u2192 Scroll horizontally to see all columns<\/p>\n\n\n\n\n\n\n\n\n
Added<\/th>\nPublisher<\/th>\nFormat<\/th>\nRepository<\/th>\nSmallest VRAM tier (build, est. memory)<\/th>\n<\/tr>\n<\/thead>\n
2026-09-18<\/td>\nbartowski<\/td>\nGGUF<\/td>\nbartowski\/nex-agi_Nex-N2.5-mini-GGUF<\/a><\/td>\nQ2_K 15.5GB (fits in 16GB VRAM)<\/td>\n<\/tr>\n
2026-09-18<\/td>\nmradermacher<\/td>\nGGUF<\/td>\nmradermacher\/Nex-N2.5-mini-GGUF<\/a><\/td>\nQ2_K 14.5GB (fits in 16GB VRAM)<\/td>\n<\/tr>\n
2026-09-18<\/td>\nmlx-community<\/td>\nMLX<\/td>\nmlx-community\/Nex-N2.5-mini-OptiQ-4bit<\/a><\/td>\nMLX 4bit 25.8GB (fits in 32GB VRAM)<\/td>\n<\/tr>\n
2026-09-18<\/td>\nmlx-community<\/td>\nMLX<\/td>\nmlx-community\/Nex-N2.5-mini-oQ4<\/a><\/td>\nMLX 22.8GB (fits in 24GB VRAM)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

This section is appended automatically by Local Model Watch when a converted build of this model appears after publication. Memory figures are estimated from the size of the distributed files.<\/em><\/p>\n

Articles (newest first)<\/h2>\n
\n\n\n\n\n\n\n
Published<\/th>\nModel<\/th>\nType<\/th>\nArticle<\/th>\n<\/tr>\n<\/thead>\n
2026-09-12<\/td>\nbartowski\/nex-agi_Nex-N2.5-mini-GGUF<\/td>\nNew Models<\/td>\nbartowski\/nex-agi_Nex-N2.5-mini-GGUF: Specs and Hardware<\/a><\/td>\n<\/tr>\n
2026-09-09<\/td>\nnex-agi\/Nex-N2.5-mini<\/td>\nNew Models<\/td>\nNex-AGI Releases Open-Weight Long-Task Model Nex-N2.5-mini<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Repositories<\/h2>\n