• Trends
  • Topics
  • Nodes
Search for keywords, #hashtags, $sites, add a dash to exclude, e.g. -$theonion.com

From ollama.com

justinledwards/mistral-small-3.1-Q6_K

1 1

Mistral Small 3.1 24B quantization from bartowski Q6_K with tool support

#llm

1h ago

From ollama.com

gemma3:12b

0 1

The current strongest model that fits on a single GPU.

on Mar 12

From ollama.com

Tags · gemma3

0 0

The current strongest model that fits on a single GPU.

on Mar 12

From ollama.com

gemma3

0 0

The current strongest model that fits on a single GPU.

on Mar 12

From ollama.com

qwq

0 0

QwQ is an experimental research model focused on advancing AI reasoning capabilities.

on Mar 5

From ollama.com

Minions: where local and cloud LLMs meet · Ollama Blog

0 0

Avanika Narayan, Dan Biderman, and Sabri Eyuboglu from Christopher Ré's Stanford Hazy Research lab, along with Avner May, Scott Linderman, James Zou, have developed a way to shift a substantial portion of LLM workloads to consumer devices by having small on-device models (such as Llama 3.2 with...

on Mar 1

From ollama.com

r1-1776

0 0

A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

on Feb 27

From ollama.com

bsahane/DeepSeek-R1-Distill-Llama-8B:Q4_K_M_lms

0 0

Get up and running with large language models.

on Feb 25

From ollama.com

Ollama

0 0

Get up and running with large language models.

on Feb 3

From ollama.com

deepseek-r1:671b

0 0

DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

on Jan 31

From ollama.com

OpenLLM-France/Lucie-7B-Instruct

0 0

Lucie-7B-Instruct is a fine-tuned version of Lucie-7B, an open-source, multilingual causal language model created by OpenLLM-France.

on Jan 27

From ollama.com

deepseek-r1:14b

0 0

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.

on Jan 24

From ollama.com

deepseek-r1:70b

0 0

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.

on Jan 22

From ollama.com

deepseek-r1

0 0

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.

on Jan 20

From ollama.com

Download Ollama on macOS

0 1

Download Ollama for macOS

on Jan 17

From ollama.com

vanilj/phi-4-unsloth

0 0

The Phi 4 model with fixed tokenizer from Unsloth

on Jan 9

From ollama.com

phi4

0 0

Phi 4 is a 14B parameter, state-of-the-art open model from Microsoft.

on Jan 9

From ollama.com

smallthinker

0 0

A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.

on Dec 31

From ollama.com

sailor2:1b

0 0

Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.

on Dec 23

From ollama.com

qwen2.5-coder/license

0 1

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

on Dec 18

From ollama.com

qwen2.5-coder:3b/license

0 1

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

on Dec 18

From ollama.com

alibayram/erurollm-9b-instruct

0 0

The EuroLLM project has the goal of creating a suite of LLMs capable of understanding and generating text in all European Union languages as well as some additional relevant languages.

on Dec 10

From ollama.com

llama3.3

0 0

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.

on Dec 8

From ollama.com

llama3.1

0 0

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

on Dec 7

From ollama.com

Structured outputs · Ollama Blog

0 0

Ollama now supports structured outputs making it possible to constrain a model's output to a specific format defined by a JSON schema. The Ollama Python and JavaScript libraries have been updated to support structured outputs.

on Dec 6

From ollama.com

Ollama Python library 0.4 with function calling improvements · Ollama Blog

0 0

Ollama Python library 0.4 with function calling improvements

on Nov 26

From ollama.com

qwen2.5-coder

0 0

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

on Nov 11

From ollama.com

llama3.2-vision

0 0

Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.

on Nov 8

From ollama.com

Llama 3.2 Vision · Ollama Blog

0 0

Llama 3.2 Vision

on Nov 6

From ollama.com

smollm2:360m

0 0

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.

on Nov 1

From ollama.com

smollm2

0 0

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.

on Nov 1

From ollama.com

granite-code:8b

0 0

A family of open foundation models by IBM for Code Intelligence

on Oct 24

From ollama.com

robbiemu/salamandra

0 0

Salamandra is a highly multilingual model pre-trained from scratch that comes in three different sizes — 2B, 7B, and 40B parameters — in base and instruction-tuned variants.

on Oct 21

From ollama.com

IBM Granite 3.0 models · Ollama Blog

0 0

Ollama partners with IBM to bring Granite 3.0 models to Ollama.

on Oct 21

From ollama.com

wizardlm2

0 0

State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.

on Oct 17

From ollama.com

bespoke-minicheck

0 0

A state-of-the-art fact-checking model developed by Bespoke Labs.

on Oct 10

From ollama.com

codegeex4

0 0

A versatile model for AI software development scenarios, including code completion.

on Oct 6

From ollama.com

tangotew/cheerchat

0 0

This the mood booster model tailored as a best friend.

on Oct 6

From ollama.com

llama3.2

0 0

Meta's Llama 3.2 goes small with 1B and 3B models.

on Sep 26

From ollama.com

mistral-small

0 0

Mistral Small is a lightweight model designed for cost-effective use in tasks like translation and summarization.

on Sep 18

From ollama.com

minicpm-v

0 0

A series of multimodal LLMs (MLLMs) designed for vision-language understanding.

on Sep 10

From ollama.com

reflection

0 0

A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

on Sep 7

From ollama.com

Ollama

0 0

Get up and running with large language models.

on Aug 25

From ollama.com

llava-llama3

0 0

A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.

on Aug 16

From ollama.com

zeffmuks/universal-ner

0 1

Entity Recognition with Fine-Tuned LLaMA 2 7B

on Aug 11

From ollama.com

deepseek-coder-v2

0 1

An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

on Aug 10

From ollama.com

llama3.1:70b

0 0

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

on Aug 2

From ollama.com

llama3.1:8b-instruct-q8_0

0 1

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

on Jul 26

From ollama.com

mistral-large

0 0

Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.

on Jul 26

From ollama.com

llama3.1

0 0

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

on Jul 24