LLM EXPLORER 63,529 MODELS INDEXED

Qwen2Vanilla GPTQ 8bits by SylvainShan

By SylvainShan · 5 downloads
HF Repo ↗ Copy URL

Qwen2Vanilla GPTQ 8bits is an open-source language model by SylvainShan. Features: 0.5b LLM, VRAM: 0.9GB, Context: 32K, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

  Arxiv:1910.09700   8-bit   Conversational   Endpoints compatible   Gptq   Instruct   Quantized   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/SylvainShan/Qwen2Vanilla_GPTQ_8bits 

Qwen2Vanilla GPTQ 8bits Parameters and Internals

LLM NameQwen2Vanilla GPTQ 8bits
Repository 🤗https://huggingface.co/SylvainShan/Qwen2Vanilla_GPTQ_8bits 
Model Size0.5b
Required VRAM0.9 GB
Updated2026-07-22
MaintainerSylvainShan
Model Typeqwen2
Instruction-BasedYes
Model Files  0.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2Vanilla GPTQ 8bits

Best Alternatives
Context / RAM
Downloads
Likes
...wen2.5 0.5B Instruct GPTQ Int432K / 0.5 GB19019
... Coder 0.5B Instruct GPTQ Int432K / 0.5 GB3211
Qwen2 0.5B Instruct GPTQ Int432K / 0.7 GB536515
... Coder 0.5B Instruct GPTQ Int832K / 0.6 GB1081
...wen2.5 0.5B Instruct GPTQ Int832K / 0.6 GB55910
Qwen2Vanilla GPTQ 4bits32K / 0.7 GB50
Qwen2 0.5B Instruct GPTQ Int832K / 1.5 GB484
...motion Classifier Qwen2.5 0.5B32K / 1 GB2941
QWev232K / 1 GB2490
Qwen Dumb Merged32K / 1 GB3090
Note: green Score (e.g. "73.2") means that the model is better than SylvainShan/Qwen2Vanilla_GPTQ_8bits.