drumih/turbo-fieldfare
- Source
- GitHub
- First trending
- Category
- Model inference
- GitHub stars
- 6,754
- Main language
- Swift
This page introduces an external open-source repository. It is not an HDATF product.
What it does
A Swift and Metal runtime that runs Gemma 4 26B-A4B on Apple Silicon Macs in about 2 GB of RAM. It keeps the shared core and KV cache in memory and streams only the needed experts from SSD.
How it helps ATF
Loosely related to our products, and it targets Apple Silicon Macs. It could still be a reference for AX consulting on how a large model can run on hardware with little memory.
License
Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.
More in this category
- MoonshotAI/Kimi-K3
Kimi K3 is an open-weight multimodal Mixture-of-Experts model with 2.8T total and 104B activated parameters and a 1-million-token context window. It understands text, images and video and targets long-horizon coding, knowledge work and reasoning. - lidge-jun/opencodex
opencodex is a local proxy that translates the Codex Responses API into other providers' formats, including streaming and tool calls. It lets Codex, Claude Code, Claude Desktop and Grok Build run models such as Gemini, DeepSeek or Ollama models. - lyogavin/airllm
AirLLM lowers the GPU memory needed for large language model inference by loading model layers one at a time, so a 70B model can run on a single 4GB GPU without quantization, distillation or pruning. Training support was added too. - Robbyant/lingbot-map
A feed-forward model for streaming 3D reconstruction. Its Geometric Context Transformer uses anchor context, a pose reference window and trajectory memory to correct drift over long frame sequences. - FareedKhan-dev/kimi-k3-in-c
A portable C99 engine that runs Kimi K3 inference on one CPU with no GPU, BLAS or framework, streaming the model from disk. The readme reports an 8.24 GB peak memory use, with more RAM only adding speed.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.