ashhart/TensorFold is one of the open-source repositories TopGit tracks, currently at 1.9k stars, written primarily in Zig. LLM Inference Engine for Metal, CUDA and Vulkan.
Snapshot summary built from the project's own GitHub metadata — there's no written TopGit review yet. The page will update automatically when a full review is published.
WHY NO REVIEW YET
TopGit writes full reviews for the most-starred, most-requested repositories. This page is a snapshot until then — see the READ ME tab for the original README in full.
TensorFold serves language models from a Zig binary on Apple Silicon and NVIDIA GPUs.
The engine reads checkpoints, tokenizes requests and runs Metal or CUDA kernels directly.
Serving needs no Python or MLX installation.
Building with a coding agent? Have it load the contributor skill and follow CONTRIBUTING.md.
Quick start
Start with Qwen3.5-2B, a small 4-bit checkpoint. The commands below download its pinned revision, then serve it as
local-model. Model weights have their own licenses.
Leave the server running. In another terminal, on either platform:
curl -fsS http://127.0.0.1:8080/v1/chat/completions \
-H 'Content-Type: application/json' \
-d '{"model":"local-model","messages":[{"role":"user","content":"Say hello in one sentence."}],"max_tokens":128,"temperature":0}'
The API also serves completions, Responses and Anthropic Messages. /v1/models lists the served name.
To talk to a model in the terminal in one command, tensorfold chat MODEL starts the server itself, streams each
reply and stops the server when the chat ends; /help lists the chat's commands, and /bye or Ctrl-D ends it:
tensorfold chat mlx-community/Qwen3.5-2B-MLX-4bit
With the server above still running, tensorfold chat --url http://127.0.0.1:8080 chats with it instead, and
echo "Say hello." | tensorfold chat --url http://127.0.0.1:8080 prints one reply for a script.
See the chat command for its flags and the serve flags it passes on.
Docs
Run guide: platform setup, requests, parallel requests, exact decoding, context compaction,
Cortheon mode, every serve flag, the Mac app and TensorFold Starlight.
Supported models: which checkpoints run on which machines, models on disk and model discovery.
Living Weights (experimental): teach a running model new facts in its own weights.
Installation runbook: macOS and CUDA installation, paired Metal serving and troubleshooting.
Windows, TensorFold Web and the Mac app.
API, Cortheon mode and known issues.
Evaluating TensorFold and community benchmarks.
Usable memory profiles: how to record applied budgets, context, cache state and process peaks.
Contributing: ATC and agents, builds, tests and the exactness and performance gates.
Changes, 1.0.0 release notes and the Zig engine preview.
TensorFold is Apache-2.0: LICENSE, NOTICE, THIRD_PARTY_NOTICES.md and SECURITY.md.
Contributors
Thank you to everyone who has sent TensorFold a pull request, a measurement or a bug report:
The most recent commit recorded on ashhart/TensorFold was 7 days ago, based on the GitHub push timestamp. The repository has 392 forks — one of the better signals of community interest.
How many stars does ashhart/TensorFold have?
ashhart/TensorFold has 1.9k GitHub stars — refresh the page for the live number, or check github.com/ashhart/TensorFold. TopGit mirrors GitHub's count but does not claim minute-by-minute accuracy.
What is ashhart/TensorFold?
ashhart/TensorFold (ashhart/TensorFold) is a Zig project on GitHub. From the project's own README: LLM Inference Engine for Metal, CUDA and Vulkan.
What language is ashhart/TensorFold written in?
ashhart/TensorFold is written primarily in Zig. GitHub's language field is based on the largest share of bytes in the default branch.
What topics is ashhart/TensorFold associated with?
GitHub's repository topics for ashhart/TensorFold: "ai", "ai-tools", "llm", "llm-inference", "llm-tools". TopGit's editorial category is open-source.
Read full README in the tab above.
Still deciding about TensorFold?
One click hands the question to an AI along with this page — see what it says about TensorFold.