Skip to main content
← Back to news

Ollama v0.34.4: faster structured outputs and faster Qwen on Apple Silicon

On-device & edge
Source:Ollama (GitHub Releases)
Ollama's v0.34.4 release applies structured outputs on thinking models in a single pass (faster and more reliable), fixes 'model not found' errors with large local libraries, and speeds up Qwen 3.8 prompt processing on Apple Silicon. A useful update if you run Ollama in production.
Read original article

Related articles

Qwen: the open model with the best multilingual support

Qwen is the open family with the best support for Italian and French: generations, sizes, MoE, when to use it, and a quick comparison with Llama.

Running LLM Models Locally: From First Install to First Working Model

From zero to a first answering model: what you actually need, Ollama step by step, how to pick a model for your memory, expected speeds per hardware, and the typical problems fixed.

Local Image Models: from SDXL to Qwen-Image

From SDXL's 2.6B parameters to Qwen-Image 2.1's 7B: how diffusion models work, how much VRAM you actually need, and which model to pick for your hardware.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

Bespoke Nimble 9B

Models

Bespoke Labs' 9B decision model: it runs entirely locally via Ollama 0.35 and answers typed questions (true/false, numeric scale, multiple choice) through the new systemone API. Built for fast classification in automated pipelines, no cloud.

🌱

Bonsai-2 27B

Models

27B reasoning model with ternary weights at 1.72 bits per weight, derived from Qwen3.8-27B with hybrid attention (~75% linear). In GGUF PTQ1_0 it takes 5.95 GB, retains 98.2% of the FP16 intelligence and reaches ~47 tok/s on an Apple M5 Max laptop, with a 262K-token context. Apache 2.0 license. Requires Prism ML's llama.cpp fork (ternary kernels are not in stock llama.cpp).

🧠

Qwen2.5 0.5B

Models

Ultra-compact 0.5B-parameter model. Runs on any hardware, even embedded: ideal for lightweight summarization and low-power local devices.

🧠

Qwen2.5 14B

Models

Clear step up in reasoning and instruction quality over 8B models. Excellent for coding, agents and structured writing on 16GB GPUs or Macs with 32GB RAM.

Browse all resources