LLM EXPLORER 67,627 MODELS INDEXED

Qwen3.8 27B AWQ by nicosuter

By nicosuter · 335936 downloads

Qwen3.8 27B AWQ is an open-source language model by nicosuter. Features: 27b LLM, VRAM: 20.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.36.

  4-bit   Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Compressed-tensors   Conversational Dataset:huggingfacefw/fineweb-... Dataset:huggingfacem4/the caul... Dataset:lambda/hermes-agent-re... Dataset:nvidia/nemotron-post-t...   Dataset:nvidia/open-swe-traces   Endpoints compatible   Eval-results   Hermes-agent   Image-text-to-text   Int4   Int8   Llm-compressor   Long-context   Mixed-precision   Mtp   Multimodal   Quantized   Qwen3 5   Qwen3 6   Qwen3 8   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Tool-use   Vllm   W4a16

Qwen3.8 27B AWQ Parameters and Internals

LLM NameQwen3.8 27B AWQ
Repository πŸ€—https://huggingface.co/nicosuter/Qwen3.8-27B-AWQ 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM20.7 GB
Updated2026-11-16
Maintainernicosuter
Model Typeqwen3_5
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   5.0 GB: 3-of-5   3.2 GB: 4-of-5   2.5 GB: 5-of-5   0.8 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.16.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B AWQ INT40K / 20.4 GB2563390103
Qwen3.6 27B AWQ0K / 22 GB66892424
Qwen3.6 27B AWQ 4bit0K / 18.7 GB2603423
Qwen3.6 27B AWQ BF16 INT40K / 28.3 GB41917141
Qwen3.8 27B AWQ INT40K / 21 GB2101532
...wen3.6 27B Abliterated AWQ MTP0K / 18.4 GB24497812
Qwen3.5 27B AWQ0K / 21.9 GB37092044
Qwen3.6 27B AWQ INT40K / 20.4 GB2785301
Qwen3.5 27B AWQ 4bit0K / 20 GB27906442
Qwen3.8 27B AWQ W4A16 ASYM0K / 0.8 GB232164
Note: green Score (e.g. "73.2") means that the model is better than nicosuter/Qwen3.8-27B-AWQ.