LLM EXPLORER 65,999 MODELS INDEXED

Sage A1.5 6bit XL MTP Mlx by leonsarmiento

By leonsarmiento · 120 downloads
HF Repo ↗ Copy URL

Sage A1.5 6bit XL MTP Mlx is an open-source language model by leonsarmiento. Features: 36b LLM, VRAM: 30.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  6-bit   6bit   Agentic Base model:internscience/sage-... Base model:quantized:internsci...   Basequant-xl   Conversational   Image-text-to-text   Mlx   Mlx-vlm   Moe   Mtp   Multimodal   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/leonsarmiento/Sage-A1.5-6bit-XL-MTP-mlx 

Sage A1.5 6bit XL MTP Mlx Parameters and Internals

LLM NameSage A1.5 6bit XL MTP Mlx
Repository 🤗https://huggingface.co/leonsarmiento/Sage-A1.5-6bit-XL-MTP-mlx 
Base Model(s)  InternScience/Sage-A1.5   InternScience/Sage-A1.5
Model Size36b
Required VRAM30.5 GB
Updated2026-10-28
Maintainerleonsarmiento
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-6   5.3 GB: 2-of-6   5.3 GB: 3-of-6   5.3 GB: 4-of-6   5.3 GB: 5-of-6   4.0 GB: 6-of-6
Quantization Type6bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Sage A1.5 6bit XL MTP Mlx

Best Alternatives
Context / RAM
Downloads
Likes
Sage A1.5 OQ4e Fp16 Mtp0K / 22.4 GB2511
Occamy 1.0 OQ8 Fp16 Mtp0K / 38.4 GB1131
Sage A1.50K / 70.6 GB2033266
Sage A1.5 FP80K / 37.7 GB64714
...c Quality Inspector V1.0 NVFP40K / 25.6 GB3160
Apodex 1.1 Mini FP80K / 37.6 GB23514
Apodex 1.1 Mini GPTQ Int40K / 22.9 GB17716
Affine 5eqdtdzqle Ckpt300 M40K / 142.6 GB5480
Occamy 1.0 OQ6e Mtp0K / 30.2 GB431
AdvancedMathBench AutoVerifier0K / 0.1 GB501
Note: green Score (e.g. "73.2") means that the model is better than leonsarmiento/Sage-A1.5-6bit-XL-MTP-mlx.