LLM EXPLORER 66,845 MODELS INDEXED

Qwen3 1.7B W2A16 AWQ WikiText2 by Minguinho-zeze

By Minguinho-zeze · 79 downloads
HF Repo ↗ Copy URL

Qwen3 1.7B W2A16 AWQ WikiText2 is an open-source language model by Minguinho-zeze. Features: 1.7b LLM, VRAM: 1GB, Context: 40K, License: apache-2.0, Quantized.

  Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-1.7b   Compressed-tensors   Conversational   Quantization   Quantized   Qwen3   Region:us   Safetensors   Vllm   W2a16
Model Card on HF 🤗: https://huggingface.co/Minguinho-zeze/Qwen3-1.7B-W2A16-AWQ-WikiText2 

Qwen3 1.7B W2A16 AWQ WikiText2 Parameters and Internals

LLM NameQwen3 1.7B W2A16 AWQ WikiText2
Repository 🤗https://huggingface.co/Minguinho-zeze/Qwen3-1.7B-W2A16-AWQ-WikiText2 
Base Model(s)  Qwen/Qwen3-1.7B   Qwen/Qwen3-1.7B
Model Size1.7b
Required VRAM1 GB
Updated2026-11-09
MaintainerMinguinho-zeze
Model Typeqwen3
Model Files  1.0 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 1.7B W2A16 AWQ WikiText2

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 1.7B W2A16 AWQ Trace40K / 1 GB771
Qwen3 1.7B MLX 4bit64K / 0.9 GB8684
Unsloth Qwen3 1.7B Finetune V140K / 3.4 GB2810
Zen Polish V2.1.7B 4bit40K / 1 GB361
Qwen3 1.7B Unsloth Bnb 4bit40K / 1.4 GB5371012
Distill 1.7B 4bit MLX40K / 1.1 GB1790
Qwen3 1.7B 4bit40K / 1 GB140826
Qwen3 1.7B Bnb 4bit40K / 1.4 GB32275
Qwen3 1.7B 4bit DWQ 05312540K / 1 GB5962
Qwen3 1.7B MLX 8bit40K / 1.8 GB6103
Note: green Score (e.g. "73.2") means that the model is better than Minguinho-zeze/Qwen3-1.7B-W2A16-AWQ-WikiText2.