MLX models for 64GB Macs - a Vontra Collection

Vontra 's Collections

updated 8 days ago

MLX models for 64GB Macs. See notes for measured versus estimated fit; context length and concurrent requests affect memory use.

Upvote

Vontra/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bit

Text Generation • 32B • Updated 9 days ago • 178

Note Published M3 Studio measurement: 17.95 GB peak, 168.41 tokens/s median; three 256-token runs after warm-up. About 46 GB nominal headroom on 64GB; longer prompts need more memory. See the card for runtime and setup.
Vontra/Qwen3.8-27B-MLX-4bit

Image-Text-to-Text • 27B • Updated 9 days ago • 594

Note Published M3 Studio peak: 20.14 GB; median decode: 39.90 tokens/s. About 43 GB nominal headroom on 64GB. See the card for benchmark conditions, runtime and setup; context increases memory.
Vontra/Muse-Glimmer-30B-MLX-4bit

Image-Text-to-Text • 30B • Updated 9 days ago • 132

Note Published M3 Studio peak: 21.33 GB; median decode: 37.70 tokens/s. About 42 GB nominal headroom on 64GB. See the card for Muse runtime support and benchmark conditions.
Vontra/Nex-N2.5-mini-MLX-4bit

Image-Text-to-Text • 35B • Updated 8 days ago • 136

Note Estimated 64GB fit; tested on a 256GB Studio with oMLX 0.6.4, not a 64GB Mac. Peak request memory was not measured. Start with short context and one request; see the card for sampling settings and quality limitations.
Vontra/Nex-N2.5-mini-MLX-6bit

Image-Text-to-Text • 35B • Updated 8 days ago • 148 • 1

Note Estimated 64GB fit; tested on a 256GB Studio with oMLX 0.6.4, not a 64GB Mac. Peak request memory was not measured. Start with short context and one request; see the card for sampling settings and quality limitations.
Vontra/Nex-N2.5-mini-MLX-8bit

Image-Text-to-Text • 35B • Updated 8 days ago • 239 • 1

Note Estimated 64GB fit; tested on a 256GB Studio with oMLX 0.6.4, not a 64GB Mac. Peak request memory was not measured. Start with short context and one request; see the card for sampling settings and quality limitations.
Vontra/Nex-N2.5-mini-MLX-oQ2

Image-Text-to-Text • 35B • Updated 8 days ago • 203 • 1

Note Estimated 64GB fit; tested on a 256GB Studio with oMLX 0.6.4, not a 64GB Mac. Peak request memory was not measured. Start with short context and one request; see the card for sampling settings and quality limitations.
Vontra/Nex-N2.5-mini-MLX-oQ3

Image-Text-to-Text • 35B • Updated 8 days ago • 71

Note Estimated 64GB fit; tested on a 256GB Studio with oMLX 0.6.4, not a 64GB Mac. Peak request memory was not measured. Start with short context and one request; see the card for sampling settings and quality limitations.
Vontra/Nex-N2.5-mini-MLX-oQ4

Image-Text-to-Text • 35B • Updated 8 days ago • 256

Note Estimated 64GB fit; tested on a 256GB Studio with oMLX 0.6.4, not a 64GB Mac. Peak request memory was not measured. Start with short context and one request; see the card for sampling settings and quality limitations.
Vontra/Nex-N2.5-mini-MLX-oQ6

Image-Text-to-Text • 35B • Updated 8 days ago • 208 • 1

Note Estimated 64GB fit; tested on a 256GB Studio with oMLX 0.6.4, not a 64GB Mac. Peak request memory was not measured. Start with short context and one request; see the card for sampling settings and quality limitations.
Vontra/Nex-N2.5-mini-MLX-oQ8

Image-Text-to-Text • 35B • Updated 8 days ago • 187 • 1

Note Estimated 64GB fit; tested on a 256GB Studio with oMLX 0.6.4, not a 64GB Mac. Peak request memory was not measured. Start with short context and one request; see the card for sampling settings and quality limitations.

Upvote