LLM EXPLORER 59,420 MODELS INDEXED

Stablecode Completion Alpha 3B 4K GGML by TheBloke

By TheBloke · 6 downloads
HF Repo ↗ Copy URL

Stablecode Completion Alpha 3B 4K GGML is an open-source language model by TheBloke. Features: 3b LLM, VRAM: 1.6GB, License: apache-2.0, Quantized, Code Generating, LLM Explorer Score: 0.08.

  Arxiv:1910.02054   Arxiv:2104.09864 Base model:finetune:stabilitya... Base model:stabilityai/stablec...   Code   Codegen   Dataset:bigcode/starcoderdata   Ggml   Gpt-neox   Model-index   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GGML 

Stablecode Completion Alpha 3B 4K GGML Parameters and Internals

Model Type 
Causal Language Model
Additional Notes 
Not compatible with llama.cpp, text-generation-webui or llama-cpp-python.
Supported Languages 
Code ()
Training Details 
Data Sources:
bigcode/starcoder-data
Data Volume:
300B tokens
Context Length:
4096
Model Architecture:
3 billion parameter decoder-only model
Input Output 
Input Format:
Custom prompt
LLM NameStablecode Completion Alpha 3B 4K GGML
Repository 🤗https://huggingface.co/TheBloke/stablecode-completion-alpha-3b-4k-GGML 
Model CreatorStabilityAI
Base Model(s)  ...blecode Completion Alpha 3B 4K   stabilityai/stablecode-completion-alpha-3b-4k
Model Size3b
Required VRAM1.6 GB
Updated2026-08-06
MaintainerTheBloke
Model Typegpt-neox
Model Files  1.6 GB   1.7 GB   1.9 GB   2.1 GB   3.0 GB
Supported Languagescode
GGML QuantizationYes
Quantization Typeggml
Generates CodeYes
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Stablecode Completion Alpha 3B 4K GGML

Best Alternatives
Context / RAM
Downloads
Likes
...blecode Instruct Alpha 3B GGML0K / 1.6 GB243
Qwen2.5 Coder 3B Unsloth Lora0K / 0.1 GB71
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/stablecode-completion-alpha-3b-4k-GGML.