phi4 · Ollama

phi4-mini

Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.

tools 3.8b

1.1M Pulls 5 Tags Updated 1 year ago

rubinmaximilian/Monk-Router-phi4mini

A high-precision, hardware-aware router built on Phi-4 Mini (3.8B). It acts as a dispatcher for local AI setups, automatically deciding whether a prompt should run on edge hardware (like a Jetson Nano), a local GPU, or the cloud based on task complexity.

tools

12 Pulls 1 Tag Updated 1 week ago

mychen76/phi4_cline_roocode

Quantized version of Phi4-14B optimized for tool usage with Cline / Roo Code and complex problem solving.

tools 14b

1,014 Pulls 4 Tags Updated 11 months ago

freakycoder123/phi4-fc

tools

127 Pulls 1 Tag Updated 7 months ago

huihui_ai/phi4-mini-abliterated

Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.

tools 3.8b

5,664 Pulls 5 Tags Updated 1 year ago

jacob-ebey/phi4-tools

Phi4 with tool support

tools

2,753 Pulls 1 Tag Updated 1 year ago

zac/phi4-tools

Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft. Clone of `phi4` with a tool calling template.

tools

1,712 Pulls 1 Tag Updated 1 year ago

sam860/phi4-mini

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.

tools 3.8b

446 Pulls 3 Tags Updated 1 year ago

doomgrave/phi-4

phi4:14b, with working tools, quantized to Q2_K and Q3_K_S for GPU with 8gb Vram or less.

tools

247 Pulls 3 Tags Updated 1 year ago

robinji/phi4-mini

tools

197 Pulls 1 Tag Updated 1 year ago

neotherack/phi4_tools

Tool enabled, quantized version Q2_K of Phi4:14b

tools

141 Pulls 1 Tag Updated 1 year ago

MHKetbi/Unsloth-Phi-4-mini-instruct

Phi-4-mini-instruct with Unsloth fixes, works on ollama v0.5.13-rc4, available in [F16, q8_0]

tools

816 Pulls 2 Tags Updated 1 year ago

pielee/qwen3-4b-thinking-2507_q8

Qwen3-4B-Thinking-2507_q8: A 4-billion-parameter inference model with 8-bit quantization, optimized for efficient reasoning in resource-constrained environments.

tools thinking

1,035 Pulls 1 Tag Updated 7 months ago

htdevs/phinegpt

PhineGPT is a custom AI assistant model built on top of Gemma4 31B using Ollama. It is designed as a general-purpose assistant optimized for accuracy, structured reasoning, and developer-friendly output.

vision tools thinking

16 Pulls 1 Tag Updated 2 days ago

prutser/gemma-4-26B-A4B-it-ara-abliterated

Gemma 4 abliterated Quants (from https://huggingface.co/jenerallee78/gemma-4-26B-A4B-it-ara-abliterated)

tools thinking

3,664 Pulls 6 Tags Updated 1 week ago

cajina/gemma4_e2b-q4_k_s

Gemma4 model 2B parameters with Q4_K_S quatization. Thinking removed. Context set to 4096

tools thinking

421 Pulls 1 Tag Updated 1 week ago

jlesbegu/evalllm2025_v2

finetuned : python -m mlx_lm.lora --train --model mistralai/Mistral-7B-Instruct-v0.3 --batch-size 4 --fine-tune-type dora --iters 1000 --num-layers 16

tools

26 Pulls 1 Tag Updated 11 months ago