LLM EXPLORER 68,192 MODELS INDEXED

Swift 1.5 Hermes Adapted Exl3 6.00bpw by TendieLabs

By TendieLabs · 25 downloads

Swift 1.5 Hermes Adapted Exl3 6.00bpw is an open-source language model by TendieLabs. Features: 27b LLM, VRAM: 22.8GB, License: other, LLM Explorer Score: 0.29.

  6-bit Base model:harness-hub/qwen3.8... Base model:quantized:harness-h...   Conversational   Efficient-thinking   Endpoints compatible   Exl3   Image-text-to-text   Post-training   Qwen3 5   Qwen3 8   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Terminal-bench   Token-efficient

Swift 1.5 Hermes Adapted Exl3 6.00bpw Parameters and Internals

LLM NameSwift 1.5 Hermes Adapted Exl3 6.00bpw
Repository πŸ€—https://huggingface.co/TendieLabs/Swift-1.5-hermes-adapted-exl3-6.00bpw 
Base Model(s)  ukisai/Swift-1.5-Qwen3.8-27b   harness-hub/Qwen3.8-27B-hermes-adapted   ukisai/Swift-1.5-Qwen3.8-27b   harness-hub/Qwen3.8-27B-hermes-adapted
Model Size27b
Required VRAM22.8 GB
Updated2026-11-21
MaintainerTendieLabs
Model Typeqwen3_5
Model Files  8.6 GB: 1-of-3   8.6 GB: 2-of-3   5.6 GB: 3-of-3
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Swift 1.5 Hermes Adapted Exl3 6.00bpw

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB863
... 27B 6.3bpw RCO SAR Marlin MTP256K / 22 GB841
Qwen3.8 27B NPU2256K /  GB2524
...toTrust Decider Pro Vision 27B0K / 55.6 GB15373904526
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB220432237
Qwen3.6 27B0K / 55.4 GB67281382197
DaisyRose 27B0K / 55.6 GB166170
Arete 27B0K / 54.7 GB2407346
Note: green Score (e.g. "73.2") means that the model is better than TendieLabs/Swift-1.5-hermes-adapted-exl3-6.00bpw.