ramalama
by containersIn its repository's words: “RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.”
Facts from GitHub
- Licence
- MIT (MIT License), permissive, our reading
- Activity
- Last push 14 Nov 2026: pushed to in the last 90 days
- Latest release
- v0.26.04 Nov 2026
- Stars
- 3.1k
- Main language
- Python
- On GitHub since
- 24 Jul 2024
- Topics
- ai, containers, cuda, hacktoberfest, hip, inference-server, intel, llamacpp, llm, podman, vllm
What it says it supports
- Loads
- GGUF, safetensors
- Runs on
- Linux, macOS
- Hardware
- NVIDIA, AMD, Apple silicon, Intel, CPU only
Each item is on our list for this tool and named in its README. A mention is not a test: check the project's documentation for your setup.
Reviewed models it can load
Matched by file format only, from our snapshot of the Hub: GGUF where we measured GGUF files, other formats where a conversion exists, safetensors for the original weights. Support for a new architecture can lag behind its release.
GGUF 386
openai-community/gpt2, Qwen/Qwen3-0.6B, Qwen/Qwen3-14B, deepseek-ai/DeepSeek-V3.2, Qwen/Qwen3.8-27B, Qwen/Qwen3.5-9B, Qwen/Qwen2.5-7B-Instruct, zai-org/GLM-5.3-Flash, Qwen/Qwen3-VL-8B-Instruct, google/gemma-4-31B-it, Qwen/Qwen3-8B, baidu/Unlimited-OCR, and 374 more, most downloaded first
safetensors 428
openai-community/gpt2, microsoft/Florence-2-base, Qwen/Qwen3-0.6B, Qwen/Qwen3-14B, deepseek-ai/DeepSeek-V3.2, Qwen/Qwen3.8-27B, Qwen/Qwen3.5-9B, Qwen/Qwen2.5-7B-Instruct, zai-org/GLM-5.3-Flash, Qwen/Qwen3-VL-8B-Instruct, google/gemma-4-31B-it, Qwen/Qwen3-8B, and 416 more, most downloaded first
Other tools in Run locally
Tool data from the GitHub API, fetched 19 Nov 2026, 15:34 UTC. Listing is not endorsement and nobody can pay to be listed. Something wrong here? Write to hello@weightsnotwalls.com.