rexmhall09

rexmhall09/TUFF

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

20 good first / help-wanted issues · Swift · last activity Oct 5, 2026

49 stars 4 forks 49 watchers Swift Apache License 2.0
apple-silicon gemma gpt-oss large-language-models llm llm-inference local-ai local-inference local-llm local-llms macos macos-app metal mixture-of-experts model-offloading moe on-device-ai openai-compatible qwen swift
20 Open Issues Need Help Last updated: Oct 5, 2026

Open Issues Need Help

View All on GitHub
help wanted good first issue area: build
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted area: server area: build
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted performance area: inference
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted performance area: inference area: server
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted performance area: inference area: server
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted good first issue area: server
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted performance area: server
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted performance area: inference
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted performance area: inference
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted performance area: inference
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
documentation help wanted area: server
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
accessibility help wanted
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
accessibility enhancement help wanted area: chat
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted performance
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted good first issue area: chat
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted good first issue area: chat
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
documentation help wanted good first issue area: cli
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted good first issue area: inference
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift
help wanted good first issue area: build
rexmhall09/TUFF
49

Turbo Ultimate Field Fare is a MacOS app that lets users run models like Qwen, Gemma, and GPT-OSS models with expert-streaming, allowing for large models on devices without a lot of memory.

Swift
#apple-silicon#gemma#gpt-oss#large-language-models#llm#llm-inference#local-ai#local-inference#local-llm#local-llms#macos#macos-app#metal#mixture-of-experts#model-offloading#moe#on-device-ai#openai-compatible#qwen#swift