LLM EXPLORER 59,420 MODELS INDEXED

QwQ 32B Preview GPTQ 4bit by ModelCloud

By ModelCloud · 306 downloads
HF Repo ↗ Copy URL

QwQ 32B Preview GPTQ 4bit is an open-source language model by ModelCloud. Features: 32b LLM, VRAM: 16.1GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.16.

  4-bit   4bit Base model:quantized:qwen/qwq-... Base model:qwen/qwq-32b-previe...   Chat   Conversational   En   Gptq   Gptqmodel   Instruct   Int4   Modelcloud   Quantized   Qwen2   Qwq   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ModelCloud/QwQ-32B-Preview-GPTQ-4bit 

QwQ 32B Preview GPTQ 4bit Parameters and Internals

LLM NameQwQ 32B Preview GPTQ 4bit
Repository 🤗https://huggingface.co/ModelCloud/QwQ-32B-Preview-GPTQ-4bit 
Base Model(s)  QwQ 32B Preview   Qwen/QwQ-32B-Preview
Model Size32b
Required VRAM16.1 GB
Updated2024-12-02
MaintainerModelCloud
Model Typeqwen2
Model Files  1.6 GB: 1-of-67   0.0 GB: 2-of-67   1.6 GB: 3-of-67   0.3 GB: 4-of-67   0.3 GB: 5-of-67   0.3 GB: 6-of-67   0.3 GB: 7-of-67   0.3 GB: 8-of-67   0.3 GB: 9-of-67   0.3 GB: 10-of-67   0.3 GB: 11-of-67   0.3 GB: 12-of-67   0.3 GB: 13-of-67   0.3 GB: 14-of-67   0.3 GB: 15-of-67   0.3 GB: 16-of-67   0.3 GB: 17-of-67   0.3 GB: 18-of-67   0.3 GB: 19-of-67   0.3 GB: 20-of-67   0.3 GB: 21-of-67   0.3 GB: 22-of-67   0.3 GB: 23-of-67   0.3 GB: 24-of-67   0.3 GB: 25-of-67   0.3 GB: 26-of-67   0.3 GB: 27-of-67   0.3 GB: 28-of-67   0.3 GB: 29-of-67   0.3 GB: 30-of-67   0.3 GB: 31-of-67   0.3 GB: 32-of-67   0.3 GB: 33-of-67   0.3 GB: 34-of-67   0.3 GB: 35-of-67   0.3 GB: 36-of-67   0.3 GB: 37-of-67   0.3 GB: 38-of-67   0.3 GB: 39-of-67   0.3 GB: 40-of-67   0.3 GB: 41-of-67   0.3 GB: 42-of-67   0.3 GB: 43-of-67   0.3 GB: 44-of-67   0.3 GB: 45-of-67   0.3 GB: 46-of-67
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.46.3
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to QwQ 32B Preview GPTQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 32B Instruct GPTQ Int432K / 19.5 GB47852040
Qwen2.5 32B Instruct GPTQ Int832K / 35.1 GB12158314
...5 Coder 32B Instruct GPTQ Int432K / 19.5 GB2061924
...5 Coder 32B Instruct GPTQ Int832K / 35.1 GB77124
Qwen1.5 32B Chat GPTQ Int432K / 19.5 GB661631
Qwen Qwen1.5 32B 4 Bit Gptq32K / 19.2 GB80
Qwen1.5 32B Chat GPTQ Int832K / 34.9 GB101
...Logic Mix 3 32B Mlx OptiQ 5bit128K / 22.3 GB411
...pSeek R1 Distill Qwen 32B 4bit128K / 18.5 GB779551
Hydraulic Deepseek 16bit128K / 65.8 GB520
Note: green Score (e.g. "73.2") means that the model is better than ModelCloud/QwQ-32B-Preview-GPTQ-4bit.