LLM EXPLORER 61,561 MODELS INDEXED

Apax Q4 K M by acecalisto3

By acecalisto3 · 12 downloads
HF Repo ↗ Copy URL

Apax Q4 K M is an open-source language model by acecalisto3. Features: 27b LLM, VRAM: 55.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-27b   Chain-of-thought   Conversational Dataset:jackrong/qwen3.5-reaso... Dataset:nohurry/opus-4.6-reaso...   Dense   En   Q4   Quantized   Qwen   Qwen3.5   Qwen3 5   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Unsloth   Zh
Model Card on HF 🤗: https://huggingface.co/acecalisto3/apax_q4_k_m 

Apax Q4 K M Parameters and Internals

LLM NameApax Q4 K M
Repository 🤗https://huggingface.co/acecalisto3/apax_q4_k_m 
Model Nameqwen/Qwen3.5-27B
Base Model(s)  Qwen/Qwen3.5-27B   Qwen/Qwen3.5-27B
Model Size27b
Required VRAM55.2 GB
Updated2026-06-15
Maintaineracecalisto3
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-11   5.3 GB: 2-of-11   5.3 GB: 3-of-11   5.3 GB: 4-of-11   5.3 GB: 5-of-11   5.3 GB: 6-of-11   5.3 GB: 7-of-11   5.4 GB: 8-of-11   5.3 GB: 9-of-11   5.3 GB: 10-of-11   2.1 GB: 11-of-11
Supported Languagesen zh
Quantization Typeq4|q4_k
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassQwen2TokenizerFast
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Apax Q4 K M

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.8 27B MLX 5bit0K / 19.5 GB46750442
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.8 27B 8bit0K / 29.4 GB1389233
...wift Qwen3.8 27B OQ4e Fp16 Mtp0K / 17.8 GB66310
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
Qwen3.8 27B MLX 8bit0K / 29.4 GB248117
Note: green Score (e.g. "73.2") means that the model is better than acecalisto3/apax_q4_k_m.