LLM EXPLORER 66,845 MODELS INDEXED

Slonik 27B OQ8 Mtp by kakoka

By kakoka · 402 downloads
HF Repo ↗ Copy URL

Slonik 27B OQ8 Mtp is an open-source language model by kakoka. Features: 27b LLM, VRAM: 29.1GB, License: apache-2.0.

  8-bit   Base model:dglhf/slonik Base model:quantized:dglhf/slo...   Code   Conversational   Mlx   Mtp   Omlx   Postgresql   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Slonik   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kakoka/Slonik-27B-oQ8-mtp 

Slonik 27B OQ8 Mtp Parameters and Internals

LLM NameSlonik 27B OQ8 Mtp
Repository 🤗https://huggingface.co/kakoka/Slonik-27B-oQ8-mtp 
Base Model(s)  dglhf/Slonik   dglhf/Slonik
Model Size27b
Required VRAM29.1 GB
Updated2026-11-09
Maintainerkakoka
Model Typeqwen3_5
Model Files  5.1 GB: 1-of-6   5.1 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   3.9 GB: 6-of-6
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Slonik 27B OQ8 Mtp

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB863
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB220432237
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B NVFP4 DGX SPARK V20K / 19.8 GB11317113
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.8 27B0K / 55.6 GB272721
Note: green Score (e.g. "73.2") means that the model is better than kakoka/Slonik-27B-oQ8-mtp.