🦜 pokee7b-Q8_0 (GGUF)
Quantized Pokee7B model for fast Apple Silicon inference via Ollama.
Quantized pokee7b model in GGUF format for efficient local inference with
llama.cpp or Ollama.
🧠 Model Details
| Field | Value |
|---|---|
| Base model | pokee-research/pokee7b |
| Format | GGUF |
| Quantization | Q8_0 (8-bit) |
| Architecture | LLaMA-compatible decoder-only transformer |
| Parameters | ~7 B |
| Author | @alexcovo |
| License | Apache 2.0 |
⚙️ Usage (Ollama)
ollama pull alexcovo/pokee7b
ollama run alexcovo/pokee7b
- Downloads last month
- 16
Hardware compatibility
Log In
to view the estimation
8-bit