LLM EXPLORER 59,278 MODELS INDEXED

Qwen3.8 27B INT4 AWQ GPTQ Gdn4 by TelperionAI

By TelperionAI · 42 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B INT4 AWQ GPTQ Gdn4 is an open-source language model by TelperionAI. Features: 27b LLM, VRAM: 22.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Compressed-tensors   Conversational   Endpoints compatible   Gptq   Image-text-to-text   Int4   Llm-compressor   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Vllm   W4a16
Model Card on HF 🤗: https://huggingface.co/TelperionAI/Qwen3.8-27B-INT4-AWQ-GPTQ-gdn4 

Qwen3.8 27B INT4 AWQ GPTQ Gdn4 Parameters and Internals

LLM NameQwen3.8 27B INT4 AWQ GPTQ Gdn4
Repository 🤗https://huggingface.co/TelperionAI/Qwen3.8-27B-INT4-AWQ-GPTQ-gdn4 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM22.6 GB
Updated2026-08-22
MaintainerTelperionAI
Model Typeqwen3_5
Model Files  20.0 GB: 1-of-3   1.8 GB: 2-of-3   0.8 GB: 3-of-3
GPTQ QuantizationYes
AWQ QuantizationYes
Quantization Typegptq|awq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B INT4 AWQ GPTQ Gdn4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B W4A16 AWQ GPTQ0K / 26.8 GB126552
Qwen3.8 27B NVFP4 AWQ GPTQ0K / 24.7 GB413
Qwen3.8 27B INT4 AWQ GPTQ0K / 25 GB591
Qwen3.8 27B AWQ INT40K / 21 GB2101532
Qwen3.6 27B AWQ INT40K / 20.4 GB2563390103
Qwen3.8 27B AWQ 5.0bpw0K / 17.3 GB144520
Qwen3.8 27B AWQ 4bit0K / 27.7 GB118746
Qwen3.8 27B AWQ BF16 INT40K / 28.8 GB157111
Qwen3.6 27B AWQ0K / 22 GB66892424
Qwen3.6 27B AWQ BF16 INT40K / 28.3 GB41917141
Note: green Score (e.g. "73.2") means that the model is better than TelperionAI/Qwen3.8-27B-INT4-AWQ-GPTQ-gdn4.