DeepCoder 14B Preview 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  DeepCoder 14B Preview 4bit   URL Share it on

  4-bit   4bit Base model:agentica-org/deepco... Base model:quantized:agentica-...   Conversational   Dataset:likaixin/taco-verified Dataset:livecodebench/code gen... Dataset:primeintellect/verifia...   En   Mlx   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

DeepCoder 14B Preview 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepCoder 14B Preview 4bit (mlx-community/DeepCoder-14B-Preview-4bit)

DeepCoder 14B Preview 4bit Parameters and Internals

LLM NameDeepCoder 14B Preview 4bit
Repository 🤗https://huggingface.co/mlx-community/DeepCoder-14B-Preview-4bit 
Base Model(s)  DeepCoder 14B Preview   agentica-org/DeepCoder-14B-Preview
Model Size14b
Required VRAM8.3 GB
Updated2025-04-30
Maintainermlx-community
Model Typeqwen2
Model Files  5.3 GB: 1-of-2   3.0 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.47.1
Tokenizer ClassLlamaTokenizerFast
Padding Token<|end▁of▁sentence|>
Vocabulary Size152064
Torch Data Typefloat32

Best Alternatives to DeepCoder 14B Preview 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct 1M Unsloth Bnb 4bit986K / 14.3 GB2693
Qwen2.5 14B Instruct 1M 8bit986K / 15.7 GB2277
...en2.5 14B Instruct 1M Bnb 4bit986K / 9.9 GB2442
Qwen2.5 14B Instruct 1M 4bit986K / 8.3 GB1732
QwQ 14B Math V0.2128K / 29.7 GB14715
...till Qwen 14B Unsloth Bnb 4bit128K / 14.2 GB1726028
Qwen Carpmuscle V0.3128K / 29.7 GB50
DeepCoder 14B Preview 8bit128K / 15.7 GB3852
Qwen2.5 14B Unsloth Bnb 4bit128K / 12.1 GB46541
...k R1 Distill Qwen 14B Bnb 4bit128K / 9.9 GB43224
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/DeepCoder-14B-Preview-4bit.

Rank the DeepCoder 14B Preview 4bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 46860 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227