Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
6.6M Pulls 5 Tags Updated 11 months ago
Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
857.3K Pulls 9 Tags Updated 7 months ago
Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
645.8K Pulls 5 Tags Updated 9 months ago
Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
98.1K Pulls 5 Tags Updated 7 months ago
Microsoft's Phi 4 model
83.9K Pulls 5 Tags Updated 1 year ago
8,420 Pulls 5 Tags Updated 11 months ago
The Phi 4 model with fixed tokenizer from Unsloth
6,828 Pulls 8 Tags Updated 11 months ago
4,089 Pulls 5 Tags Updated 9 months ago
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft. Clone of `phi4` with a tool calling template.
1,480 Pulls 1 Tag Updated 10 months ago
1,281 Pulls 4 Tags Updated 7 months ago
Phi-4-mini-instruct with Unsloth fixes, works on ollama v0.5.13-rc4, available in [F16, q8_0]
698 Pulls 2 Tags Updated 9 months ago
Phi-4-mini is the latest small LLM from microsoft. These are the quants that I like to use, that weren't uploaded to the main model by the ollama team.
274 Pulls 3 Tags Updated 9 months ago
Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length.
224 Pulls 1 Tag Updated 8 months ago
Microsoft's Phi 4 with tokenizer fixes from Unsloth.
192 Pulls 2 Tags Updated 11 months ago
Phi-4-mini-instruct を GGUF に変換したものです。
148 Pulls 1 Tag Updated 6 months ago
144 Pulls 1 Tag Updated 10 months ago
143 Pulls 1 Tag Updated 1 year ago
fine-phi4 is a customized version of Microsoft’s Phi-4 model It can explain programming concepts, generate code snippets, and guide you through debugging or software design.
130 Pulls 1 Tag Updated 4 months ago
phi4:14b, with working tools, quantized to Q2_K and Q3_K_S for GPU with 8gb Vram or less.
127 Pulls 3 Tags Updated 8 months ago
A customized version of the phi-4 model specialized in generating secure, clean, and production-ready SQL Server queries from natural language prompts (Arabic or English). Designed by Alwaleed Alduais, this model is optimized for enterprise use cases
118 Pulls 1 Tag Updated 5 months ago