LLM EXPLORER 59,420 MODELS INDEXED

Qwen2.5 Coder 0.5B Merged by vonjack

By vonjack · 29 downloads
HF Repo ↗ Copy URL

Qwen2.5 Coder 0.5B Merged is an open-source language model by vonjack. Features: 0.5b LLM, VRAM: 1.3GB, Context: 32K, Quantized, Instruction-Based, Code Generating, Merged, LLM Explorer Score: 0.17.

  Merged Model   Arxiv:2306.01708 Base model:qwen/qwen2.5-coder-... Base model:qwen/qwen2.5-coder-...   Codegen   Conversational   Endpoints compatible   Gguf   Instruct   Q8   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/vonjack/Qwen2.5-Coder-0.5B-Merged 

Qwen2.5 Coder 0.5B Merged Parameters and Internals

LLM NameQwen2.5 Coder 0.5B Merged
Repository 🤗https://huggingface.co/vonjack/Qwen2.5-Coder-0.5B-Merged 
Base Model(s)  Qwen/Qwen2.5-Coder-0.5B   Qwen/Qwen2.5-Coder-0.5B-Instruct   Qwen/Qwen2.5-Coder-0.5B   Qwen/Qwen2.5-Coder-0.5B-Instruct
Merged ModelYes
Model Size0.5b
Required VRAM1.3 GB
Updated2026-08-05
Maintainervonjack
Model Typeqwen2
Instruction-BasedYes
Model Files  0.7 GB   1.3 GB: 1-of-1
GGUF QuantizationYes
Quantization Typeq8|gguf
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.46.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 Coder 0.5B Merged

Best Alternatives
Context / RAM
Downloads
Likes
...5 Coder 0.5B Instruct Bnb 4bit32K / 0.5 GB66124
...en2.5 Coder 0.5B Instruct 4bit32K / 0.3 GB33356
Qwen2.5 Coder 0.5B Instruct32K / 1 GB9743974
Qwen 2.5 Coder 0.5B SQL Writer32K / 1 GB130
Qwen CoMa 0.5B32K / 1.3 GB21
Qwen2.5 Coder 0.5B Instruct32K / 1 GB23215
Qwen2.5 Coder 0.5B Instruct32K / 1 GB140
Qwen2.5 Coder 0.5B Instruct32K / 1 GB50
Hammer2.1 0.5B32K / 1 GB6816
...truct PIFT Enja Manywords 800032K / 2 GB170
Note: green Score (e.g. "73.2") means that the model is better than vonjack/Qwen2.5-Coder-0.5B-Merged.