The request names "codegemma-2b", a Google model; none of the candidate sources shows that model or its weights directly. Ollama 8 runs open AI models locally and Replicate 9 hosts open-source models via API, so these are the closest ways to run an open code model, though neither source confirms CodeGemma specifically.
A question back: Do you want to run codegemma-2b locally on your own machine, or call it through a hosted cloud API?
- 1
Ollamaollama.comwebsite read, tools not yet checked
Runs open AI models locally or in the cloud on macOS, Windows and Linux 8, which is a practical route to running an open code model such as CodeGemma.
+136 community tools built for it
- 2
Replicatereplicate.comverified and signed
Runs open-source machine learning models through a cloud API 9, which could host a CodeGemma-style open model without local hardware.
for agents: andreasjansson/codegen
- 3
Mistralmistral.aiverified and signed
Offers frontier open-weight models you can run on-prem, in your VPC or in its cloud 2, an alternative family of open models for code work.
+297 community tools built for it
for agents: coding-assistant · llm · developer-tools
Sources
- 2Mistral | #1 in Sovereign AI: Frontier Open Models You Ownmistral.ai · read 2026-10-30
- 8Ollama · Run AI models locally and in the cloudollama.com · read 2026-10-29
- 9Replicate - Run AI with an APIreplicate.com · read 2026-10-29
For agents: the 10 actions behind this answer
code-exemplars-blueprint-generator · code-exemplars-blueprint-generator verified and signed
Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases and identifying high-quality code exemplars. Supports multiple programming languages (.NET, Java, JavaScript, TypeScript, React, Angular, Python) with configurable analysis depth, categorization methods,
coding-assistant · mistral-vibe verified and signed
codegen · codegen verified and signed
Code generation utilities for json-render. Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props for @json-render/codegen.
workers-ai-search-model · Cloudflare API verified and signed
Model Search
imagegen · imagegen verified and signed
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, a
notion · notion verified and signed
Notion workspace integration. Search pages, create and update documents, manage databases, and access your team's knowledge base directly from Claude Code for seamless documentation workflows.
· Playwright website read, tools not yet checked
Web automation and testing for apps, scripts, and AI agents
· Ollama website read, tools not yet checked
Ollama is the easiest way to run and build with open AI models locally or in the cloud on macOS, Windows, and Linux.
andreasjansson/codegen · andreasjansson/codegen verified and signed
An open-source model for program synthesis. Competitive with OpenAI Codex.
pydantic · pydantic verified and signed
Pydantic is a Python data validation and serialization library, based on type hints. Use this skill whenever you need to do relatively complex data modeling using Pydantic, e.g. when adding constraints, defining a model hierarchy with subclasses, etc.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.