AI Models
Explore the models available on the GabForge platform.
GabForge-Coder-v1.0-Local-1.5B
gabforge-coder-v1.0-local-1.5b
Compact code completion model. Optimized for speed on CPU. Based on Qwen2.5-Coder-1.5B with Q4_K_M quantization.
- Context
- 4,096 tokens
- Speed
- ~20 tok/s (CPU)
GabForge-Coder-v1.0-Cloud
gabforge-coder-v1.0-cloud
Full-featured cloud-hosted coding assistant. Higher quality, GPU-accelerated inference.
- Context
- 32,768 tokens
- Speed
- ~80 tok/s (GPU)
GabForge-Coder-v1.0-Enterprise
gabforge-coder-v1.0-enterprise
Maximum context enterprise model. Extended context window for large codebases.
- Context
- 262,144 tokens
- Speed
- ~60 tok/s (GPU)