LLM EXPLORER 59,420 MODELS INDEXED

Qwen2.5 14B Instruct 1M Bnb 4bit by unsloth

By unsloth · 95 downloads
HF Repo ↗ Copy URL

Qwen2.5 14B Instruct 1M Bnb 4bit is an open-source language model by unsloth. Features: 14b LLM, VRAM: 9.9GB, Context: 986K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.16.

  Arxiv:2412.15115   4-bit   4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-14b-in...   Bitsandbytes   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2.5-14B-Instruct-1M-bnb-4bit 

Qwen2.5 14B Instruct 1M Bnb 4bit Parameters and Internals

LLM NameQwen2.5 14B Instruct 1M Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Qwen2.5-14B-Instruct-1M-bnb-4bit 
Base Model(s)  Qwen/Qwen2.5-14B-Instruct-1M   Qwen/Qwen2.5-14B-Instruct-1M
Model Size14b
Required VRAM9.9 GB
Updated2026-07-28
Maintainerunsloth
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   4.9 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length1010000
Model Max Length1010000
Transformers Version4.49.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 14B Instruct 1M Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M 8bit986K / 15.7 GB43012
Qwen2.5 14B Instruct 1M 4bit986K / 8.3 GB3792
...B Instruct 1M Unsloth Bnb 4bit986K / 14.3 GB144
...n2.5 Math 14B Instruct Preview32K / 29.7 GB511
Qwen Carpmuscle V0.4.132K / 29.7 GB90
...wen2.5 Math 14B Instruct Alpha32K / 29.7 GB572
Reasoning 1 1K Demo32K / 29.7 GB381
RQwen V0.132K / 29.7 GB302
Sphinx2.032K / 29.7 GB01
Qwen Carpmuscle V0.432K / 29.7 GB91
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2.5-14B-Instruct-1M-bnb-4bit.