Nowadays you get TTS, STT, text & image generation and image editing should also be possible. Besides being able to run via rocm, vulkan or on CPU, GPU and NPU. Quite a lot of options. They have a quite good and pragmatic pace in development. Really recommend this for AMD hardware!
Edit: OpenAI and i think nowaday ollama compatible endpoints allow me to use it in VSCode Copilot as well as i.e. Open Web UI. More options are shown in their docs.
You would get similar performance. Lemonade is designed as a turnkey (optimized for AMD Hardware) for local AI models. The software helps you manage backends (llama.cpp, flm, whispercpp, stable‑diffusion.cpp, etc) for different GenAI modalities from a single utility.
I have two Strix Halo devices at hand. Privately a framework desktop with 128gb and at work 64GB HP notebook. The 64GB machine can load Qwen3.5 30B-A3B, with VSCode it needs a bit of initial prompt processing to initialize all those tools I guess. But the model is fighting with the other resources that I need. So I am not really using it anymore these days, but I want to experiment on my home machine with it. I just dont work on it much right now.
Lemonade has a Web UI to set the context size and llama.cpp args, you need to set context to proper number or just to 0 so that it uses the default. If its too low, it wont work with agentic coding.
I will try some Claw app, but first need to research the field a bit. But I am using different models on Open Web UI. GPT 120B is fast, but also Qwen3.5 27B is fine.
Qwen3-Coder-Next works well on my 128GB Framework Desktop. It seems better at coding Python than Qwen3.5 35B-A3B, and it's not too much slower (43 tg/s compared to 55 tg/s at Q4).
27B is supposed to be really good but it's so slow I gave up on it (11-12 tg/s at Q4).
Agreed. Qwen3-coder-next seems like the sweetspot model on my 128GB Framework Desktop. I seem to get better coding results from it vs 27b in addition to it running faster.
The 8 bit MLX unsloth quant of qwen3-coder-next seems to be a local best on an MBB M5 Max with 128GB memory. With oMLX doing prompt caching I can run two in parallel doing different tasks pretty reasonably. I found that lower quants tend to lose the plot after about 170k tokens in context.
That's good to know. I haven't exceeded a 120k context yet. Maybe I'll bite the bullet and try Q6 or Q8. Any of coder-next quants larger than UD-Q4_K_XL take forever to load, especially with ROCm. I think there's some sort of autotuning or fitting going in llama.cpp.
Running Qwen3.5 122B at 35t/s as a daily driver using Vulcan llama.cpp on kernel 7.0.0rc5 on a Framework Desktop board (Strix Halo 128).
Also a pair of AMD AI Pro r9700 cards as my workhorses for zimageturbo, qwen tts/asr and other accessory functions and experiments.
Finally have a Radeon 6900 XT running qwen3.5 32B at 60+t/s for a fast all arounder.
If I buy anything nvidia it will be only for compatibility testing. AMD hardware is 100% the best option now for cost, freedom, and security for home users.
With Buildplace, you can simulate your planning projects in a digital twin in no time. The integrated inventory mapping captures the complexity of your real estate portfolio and transforms it into an interactive map that you can easily enrich with additional geodata. Furthermore, our holistic consulting approach supports you with individual project planning, customized enhancements, and the targeted application of Buildplace for your specific use case.
We are a team of ~10 persons half of them engineers. This might sound small, but we are bootstrapped and try to keep our software stack observable. We program mainly in Typescript with Fastify, BullMQ, GraphQL (Pothos) on the backend, Postgres and Redis as DBs [ and React, Maplibre, BabylonJS on the frontend ].
We see demand in more expertise for container orchestration, load balancing, reverse proxy configuration, VPS Administration and monitoring.
Therefore, if you are curious about our field of work and have knowledge in system administration and / or backend engineering with the stated technologies, feel free to reach out to us!
I have AMD Strix Halo (395) on my work laptop (HP Ultrabook G1A) as well as at home with Framework Desktop.
On both i have setup lemonade-server on system start.
At work i use Qwen3 Coder 30B-3A with continue.dev. It serves me well in 90% of cases.
At home i have 128GB RAM. I try a bit GPT120B. I host Open WebUI on it and connect via https and wireguard to it, so i can use it as PWA on my phone. I love not needing to think about where my data goes. But i would like to allow parallel requests, so i need to tinker a bit more. Maybe llama-swap is enough.
I just need to see how to deal with context length. My models stop or go into infinite loop after some messages. But then i often start a new chat.
Lemonade-server runs with llama.cpp, vllm seems to be scaling better thoug, but is not so easy to set up.
Unsloth GGUFs are great resource for models.
Also for Strix Halo check out kyuz0 repositorIES! Also has image gen. I didnt try those yet. But the benchmarks are awesome! Lots to learn from.
Framework forum can be useful, too.
Btw. even a AMD HX 370 with non soldered RAM can get some nice t/s for smaller models.
Can be helpful enough when disconnected from internet and you dont know how to style a svg :)
The makers of panda css are also creators of chakra-ui.
Chakra-UI is like tailwind + ui components for react. They currently transfer their knowledge into separate packages to allow adoption by other frameworks like vue etc.
Panda seems to work a bit like chakra. I really love the convenience components/functions like Stack. But it will be combined with component ark and zag. Zag is state management for components, while ark creates headless components for vue react etc. And combined with panda we come back full circle for v3 of chakra. I am really looking forward to this. But also hope that chakra stays true to its use of basic html elements and accessibility.
The team knows what it is doing!
"FastFlowLM (FLM) support in Lemonade is in Early Access. FLM is free for non-commercial use, however note that commercial licensing terms apply. "