qwen2.5:3b
A small-parameter language model released by Alibaba's Qwen team, with 3.09B parameters under the Apache 2.0 license, suited to running locally on low-memory devices.
Timeline (last 90 days)
SoloBooks AI performs AI extraction through the local Ollama API (127.0.0.1:11434), having validated two models: llama3:latest (8.03B parameters) and qwen2.5:3b (3.09B parameters).
relnotes is not tied to a specific model service but connects to any OpenAI-compatible endpoint, uses Ollama's qwen2.5:3b model by default, and can switch to LM Studio, llama.cpp or vLLM via a flag.
In a model comparison test, qwen2.5:3b correctly understood pace, produced 0 hallucinated place names, had a length error of 0.3%, peak memory of 259 MB, and took 106 seconds.
In testing, all three models—qwen2.5:3b, qwen2.5:1.5b, and llama3.2:1b—kept model memory below 0.5 GB, and all produced 0 hallucinated place names.
All Facts (4)
SoloBooks AI performs AI extraction through the local Ollama API (127.0.0.1:11434), having validated two models: llama3:latest (8.03B parameters) and qwen2.5:3b (3.09B parameters).
50%Unverifiedrelnotes is not tied to a specific model service but connects to any OpenAI-compatible endpoint, uses Ollama's qwen2.5:3b model by default, and can switch to LM Studio, llama.cpp or vLLM via a flag.
50%UnverifiedIn a model comparison test, qwen2.5:3b correctly understood pace, produced 0 hallucinated place names, had a length error of 0.3%, peak memory of 259 MB, and took 106 seconds.
50%UnverifiedIn testing, all three models—qwen2.5:3b, qwen2.5:1.5b, and llama3.2:1b—kept model memory below 0.5 GB, and all produced 0 hallucinated place names.
50%