--- title: Improved performance and model support with GGUF ·... description: Ollama 0.30 adds GGUF model compatibility via llama.cpp, complementing its MLX engine on Apple silicon and extending support to a wider range of hardware.... canonical: https://daily.dev/posts/improved-performance-and-model-support-with-gguf-ollama-blog-dxhlivdkr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Improved performance and model support with GGUF · Ollama Blog | daily.dev og:description: Ollama 0.30 adds GGUF model compatibility via llama.cpp, complementing its MLX engine on Apple silicon and extending support to a wider range of hardware.... og:url: https://daily.dev/posts/improved-performance-and-model-support-with-gguf-ollama-blog-dxhlivdkr og:image: https://api.daily.dev/og/posts/dXhLivdkR.png og:image:alt: Improved performance and model support with GGUF · Ollama Blog og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Improved performance and model support with GGUF · Ollama Blog **[Ollama](https://daily.dev/sources/ollama)** · 2 min read · 0 upvotes · 0 comments ## Summary Ollama 0.30 adds GGUF model compatibility via llama.cpp, complementing its MLX engine on Apple silicon and extending support to a wider range of hardware. NVIDIA GPU throughput is up to 20% faster (tested with Gemma 4 26B Q4_K_M on an RTX 5090), and Vulkan is enabled by default, letting AMD and Intel GPUs run models out of the box without vendor libraries. The release also expands compatible model families (LFM, Prism, Unsloth fine-tunes) and adds one-command launches for coding agents like Claude Code, Hermes Agent, and OpenClaw when a model supports tool calling. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What's new in Ollama 0.30? Ollama 0.30 adds GGUF model compatibility through llama.cpp, complementing the existing MLX engine on Apple silicon. NVIDIA GPU performance improves up to 20% (tested with Gemma 4 26B Q4_K_M on an RTX 5090), and Vulkan is enabled by default, extending GPU acceleration to AMD and Intel hardware without needing vendor-specific libraries. _Track Ollama releases like this on daily.dev before upgrading local LLM setups._ ### How do I run a GGUF model I downloaded from Hugging Face in Ollama? Download the GGUF file, create a Modelfile containing a FROM line pointing to the GGUF path (e.g. FROM ./my-model.Q4_K_M.gguf), then run 'ollama create -f Modelfile my-model' followed by 'ollama run my-model'. This works for GGUF-format models including LFM, Prism, and Unsloth fine-tunes. _daily.dev helps developers keep up with practical guides for running local models like this._ ### How do I use a local Ollama model with Claude Code or other coding agents? If the GGUF model supports tool calling, run 'ollama launch claude --model my-model' for Claude Code, 'ollama launch hermes --model my-model' for Hermes Agent, or 'ollama launch openclaw --model my-model' for OpenClaw. Verify tool-calling support first by checking for the 'tools' capability with 'ollama show my-model'. _Developers wiring local models into coding agents can follow updates like this on daily.dev._ ## Similar posts on daily.dev - [I switched my local LLM setup to Ollama's new MLX engine, and my Mac suddenly feels twice as fast](https://daily.dev/posts/i-switched-my-local-llm-setup-to-ollama-s-new-mlx-engine-and-my-mac-suddenly-feels-twice-as-fast-3pyxiagbi) · XDA Developers · 1 upvotes · 0 comments - [New coding models & integrations · Ollama Blog](https://daily.dev/posts/new-coding-models-integrations-ollama-blog-onqkepkh1) · Hacker News · 30 upvotes · 0 comments - [GGML Joins Hugging Face: What This Means for Local Model Optimization](https://daily.dev/posts/ggml-joins-hugging-face-what-this-means-for-local-model-optimization-kcqkzh1zi) · SitePoint · 0 upvotes · 0 comments - [Open-Source AI Tool Upgrades Speed Up LLM and Diffusion Models on NVIDIA RTX PCs](https://daily.dev/posts/open-source-ai-tool-upgrades-speed-up-llm-and-diffusion-models-on-nvidia-rtx-pcs-4w4zhy3m3) · NVIDIA Developer · 2 upvotes · 0 comments --- Tags: [#vulkan](https://daily.dev/tags/vulkan), [#local-ai](https://daily.dev/tags/local-ai), [#ollama](https://daily.dev/tags/ollama), [#llama-cpp](https://daily.dev/tags/llama-cpp) [View this post on daily.dev](https://daily.dev/posts/improved-performance-and-model-support-with-gguf-ollama-blog-dxhlivdkr) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Improved performance and model support with GGUF · Ollama Blog","url":"https://daily.dev/posts/improved-performance-and-model-support-with-gguf-ollama-blog-dxhlivdkr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/improved-performance-and-model-support-with-gguf-ollama-blog-dxhlivdkr"},"datePublished":"2026-08-23T12:23:53.764Z","dateModified":"2026-08-23T12:57:32.704Z","description":"Ollama 0.30 adds GGUF model compatibility via llama.cpp, complementing its MLX engine on Apple silicon and extending support to a wider range of hardware....","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Ollama","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Ollama","logo":"https://media.daily.dev/image/upload/s--dRYYkBCj--/f_auto,q_auto/v1787487632/logos/ollama-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/ollama"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/improved-performance-and-model-support-with-gguf-ollama-blog-dxhlivdkr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"vulkan,local-ai,ollama,llama-cpp","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ollama","item":"https://daily.dev/sources/ollama"},{"@type":"ListItem","position":3,"name":"Improved performance and model support with GGUF · Ollama Blog"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/improved-performance-and-model-support-with-gguf-ollama-blog-dxhlivdkr#faq","mainEntity":[{"@type":"Question","name":"What's new in Ollama 0.30?","acceptedAnswer":{"@type":"Answer","text":"Ollama 0.30 adds GGUF model compatibility through llama.cpp, complementing the existing MLX engine on Apple silicon. NVIDIA GPU performance improves up to 20% (tested with Gemma 4 26B Q4_K_M on an RTX 5090), and Vulkan is enabled by default, extending GPU acceleration to AMD and Intel hardware without needing vendor-specific libraries. Track Ollama releases like this on daily.dev before upgrading local LLM setups."}},{"@type":"Question","name":"How do I run a GGUF model I downloaded from Hugging Face in Ollama?","acceptedAnswer":{"@type":"Answer","text":"Download the GGUF file, create a Modelfile containing a FROM line pointing to the GGUF path (e.g. FROM ./my-model.Q4_K_M.gguf), then run 'ollama create -f Modelfile my-model' followed by 'ollama run my-model'. This works for GGUF-format models including LFM, Prism, and Unsloth fine-tunes. daily.dev helps developers keep up with practical guides for running local models like this."}},{"@type":"Question","name":"How do I use a local Ollama model with Claude Code or other coding agents?","acceptedAnswer":{"@type":"Answer","text":"If the GGUF model supports tool calling, run 'ollama launch claude --model my-model' for Claude Code, 'ollama launch hermes --model my-model' for Hermes Agent, or 'ollama launch openclaw --model my-model' for OpenClaw. Verify tool-calling support first by checking for the 'tools' capability with 'ollama show my-model'. Developers wiring local models into coding agents can follow updates like this on daily.dev."}}]} ```