Releasesby GlyphOllama 0.40.16
Ripple Preview Ripple Preview from Ricursive Intelligence is a 65B dense model built for agentic coding. sh ollama run ripple-preview - Qwen3.8 Flash Next uses about 27 GiB less memory on Apple silicon - ollama launch claude always routes Claude Code to the selected model - ollama launch explains when a cloud model has been retired - /v1/responses respects...
Also shipped Nov 9, 2026Ollama in November 2026 →
The following AlloyDB AI features and improvements are generally available ( GA ): - Smart batching for AI...
The following AlloyDB AI features and improvements are generally available ( GA ): Smart batching for AI functions: AI function acceleration is generally available for ai.if , ai.rank , ai.analyze_sentiment , ai.summarize , ai.extract , ai.classify , and ai.generate on AlloyDB clusters running PostgreSQL 17 and later.
To support your FinOps practices, you can now opt in to compute cost attribution in BigQuery editions
To support your FinOps practices, you can now opt in to compute cost attribution in BigQuery editions. This feature attributes billed compute charges directly to the query projects that use your administration project's reservation capacity.
Query performance troubleshooting and job and system performance comparison in the BigQuery jobs explorer are...
Query performance troubleshooting and job and system performance comparison in the BigQuery jobs explorer are generally available (GA). For more information, see Troubleshoot job performance and Diagnose performance regressions by comparing jobs and systems .
When you create or schedule a pipeline, you can specify the maximum number of concurrently executed pipeline...
When you create or schedule a pipeline, you can specify the maximum number of concurrently executed pipeline tasks. This feature is generally available (GA).
You can use compression functions in GoogleSQL to compress or decompress bytes or string values by using the...
You can use compression functions in GoogleSQL to compress or decompress bytes or string values by using the Zstandard (Zstd) lossless data compression algorithm. The following functions are supported: ZSTD_COMPRESS ZSTD_DECOMPRESS_TO_BYTES ZSTD_DECOMPRESS_TO_STRING These functions are in Preview .
Fast mode for Anthropic Claude models is generally available
Fast mode for supported Anthropic Claude models, starting with Claude Fable 5.2 ( claude-fable-5-2 ), is available in General Availability (GA) . You can set "speed": "fast" in online pay-as-you-go prediction requests to accelerate output token generation for latency-sensitive agentic workflows.
More from OllamaEvery Ollama release →
Ollama 0.40.14
- ollama launch claude now applies the model's output token limit for Claude Code, so cloud models no longer run into the 128k default cap - Cloud web search responses on /api/chat are now decoded correctly, including compressed responses - OpenAI-compatible endpoints no longer override a model's packaged sampler defaults , clients that send no...
Ollama 0.40.15
MiMo V2.6 Xiaomi MiMo's mimo-v2.6, a 9B model built for code and agent workflows, is now supported in Ollama. sh ollama run mimo-v2.6 AutoTrust decision models AutoTrust decision models read text and return choices, yes or no probabilities, and ratings for the questions you supply.
Ollama 0.40.13
Ollama 0.40.13 now supports Liquid AI's LFM3 models, including text-to-speech capabilities, on Linux and Windows in addition to Apple silicon.
Ollama 0.40.12
Ollama 0.40.12 adds support for the Liquid AI LFM3 model family, including text, vision, audio, and omni variants. The release also includes performance improvements for Apple silicon and updated MLX and llama.cpp dependencies.
Ollama 0.40.11
Ollama now supports speech generation on macOS and introduces d3 decision models for classification and scoring tasks. The d3 family includes models ranging from 2B to 27B parameters.
Ollama 0.40.10
Ollama now supports the NVIDIA Nemotron 3.5 Bolt E4B vision-language model, which features a 128K-token context window.
Ollama 0.40.9
Ollama 0.40.9 adds speech generation on Apple Silicon, introduces the d3 decision model family, and expands Flint support to Linux and Windows. It also includes improvements to streaming responses and context length handling.
Ollama 0.40.8
Ollama release 0.40.8 adds support for Recursive's Flint coding model, an Apache 2.0-licensed 40B-parameter MoE model with a 262K-token context window optimized for repository-level coding tasks.