LLM EXPLORER 57,252 MODELS INDEXED

Qwen2.5 Channel Coder 14B Instruct by spacematt

By spacematt · 7 downloads
HF Repo ↗ Copy URL

Qwen2.5 Channel Coder 14B Instruct is an open-source language model by spacematt. Features: 14b LLM, VRAM: 29.7GB, Context: 32K, License: apache-2.0, Instruction-Based, Code Generating, Merged, LLM Explorer Score: 0.18.

  Merged Model   Arxiv:2403.19522   Autotrain compatible Base model:agentica-org/deepco... Base model:allura-org/tq2.5-14... Base model:arcee-ai/supernova-... Base model:cultrix/qwen2.5-14b... Base model:cultrix/qwen2.5-14b... Base model:netease-youdao/conf...   Base model:oxyapi/oxy-1-small Base model:sometimesanotion/la... Base model:sometimesanotion/la... Base model:spacematt/qwen2.5-a... Base model:v000000/qwen2.5-14b...   Codegen   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/spacematt/Qwen2.5-Channel-Coder-14B-Instruct 

Qwen2.5 Channel Coder 14B Instruct Parameters and Internals

LLM NameQwen2.5 Channel Coder 14B Instruct
Repository 🤗https://huggingface.co/spacematt/Qwen2.5-Channel-Coder-14B-Instruct 
Base Model(s)  sometimesanotion/Lamarck-14B-v0.7   Mergekit Sce Vjeombg   CultriX/Qwen2.5-14B-Hyperionv5   allura-org/TQ2.5-14B-Neon-v1   Oxy 1 Small   sometimesanotion/Lamarck-14B-v0.7-Fusion   CultriX/Qwen2.5-14B-ReasoningMerge   spacematt/Qwen2.5-Agile-Coder-14B-Instruct   Confucius O1 14B   SuperNova Medius   v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno   DeepCoder 14B Preview   sometimesanotion/Lamarck-14B-v0.7   mergekit-community/mergekit-sce-vjeombg   CultriX/Qwen2.5-14B-Hyperionv5   allura-org/TQ2.5-14B-Neon-v1   oxyapi/oxy-1-small   sometimesanotion/Lamarck-14B-v0.7-Fusion   CultriX/Qwen2.5-14B-ReasoningMerge   spacematt/Qwen2.5-Agile-Coder-14B-Instruct   netease-youdao/Confucius-o1-14B   arcee-ai/SuperNova-Medius   v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno   agentica-org/DeepCoder-14B-Preview
Merged ModelYes
Model Size14b
Required VRAM29.7 GB
Updated2025-08-06
Maintainerspacematt
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.8 GB: 6-of-6
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.51.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151665
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 Channel Coder 14B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB278
Qwen2.5 14B YOYO V4986K / 29.7 GB205
ZYH LLM Qwen2.5 14B V2986K / 29.7 GB141
ZYH LLM Qwen2.5 14B V5986K / 29.7 GB128
Qwen2.5 14B YOYO V5986K / 29.7 GB104
Mergekit Model Stock Ggfjmyf986K / 29.7 GB140
Mergekit Model Stock Injkqri986K / 29.7 GB51
...1 DeepSeekR1 Coder 14B Preview128K / 29.7 GB93
Tessa T1 14B117K / 29.7 GB613
UIGEN T1.5 14B117K / 29.7 GB86
Note: green Score (e.g. "73.2") means that the model is better than spacematt/Qwen2.5-Channel-Coder-14B-Instruct.