I have been so far happy with the value that Copilot brought but for the past few weeks I have felt the chokehold on the number of requests.
I have had the chance to test the main Chinese models through OpenRouter but the Pay-as-you-go model is expensive compared to a subscription model, but I don't want to marry to a single provider.
Thanks for bringing OpenCode Go to my attention. Your comparison is the research I didn't know I needed, and I will be cancelling my Copilot subscription to replace it with OpenCode Go right away.
I am definitely looking forward to TurboQuant. Makes me feel like my current setup is an investment that could pay over time. Imagine being able to run models like MiniMax M2.5 locally at Q4 levels. That would be swell.
Not the answer that you are looking for, but I am a fellow AMD GPU owner, so I want to share my experience.
I have a 9070 XT, which has 16GB of VRAM.
My understanding from reading around a bunch of forums is that the smallest quant you want to go with is Q4. Below that, the compression starts hurting the results quite a lot, especially for agentic coding. The model might eventually start missing brackets, quotes, etc.
I tried various AI + VRAM calculators but nothing was as on the point as Huggingface's built-in functionality. You simply sign up and configure in the settings [1] which GPU you have, so that when you visit a model page, you immediately see which of the quants fits in your card.
From the open source models out there, Qwen3.5 is the best right now. unsloth produces nice quants for it and even provides guidelines [2] on how to run them locally.
The 6-bit version of Qwen3.5 9B would fit nicely in your 6700 XT, but at 9B parameters, it probably isn't as smart as you would expect it to run.
Which model have you tried locally? Also, out of curiosity, what is your host configuration?
I am legitimately curious about the parameters that the person used for running the model locally to get the results they got because I am myself currently experimenting with running models locally myself. You can see I am asking similar questions to others in this same thread and correlate the timestamps.
Apparently there is a whole science behind running models. I have seen the instructions that unsloth publishes for their quants and depending on the model they'll tweak things like the temperature, top k, etc.
The size of the quantization you chose also makes a difference.
The GPU driver also plays an important role.
What was your approach? What software did you use to run the models?
> [...] _but not necessarily use the right format._
This has also been my experience. But isn't the harness sending the instructions on how to invoke a tool? Maybe it is missing the formatting part. What do you think?
Through my Kagi subscription I get access to quite a few models [1] but I tend to rely on Qwen3 (fast) for quick questions and Qwen3 (reasoning) when I want a more structured approach, for example, when I am researching a topic.
I have tried the same approach with Kimi K2.5 and GLM 5 but I keep going back fo Qwen3.
I also have access to Perplexity which is quite decent to be honest, but I prefer to keep everything in Kagi.
> [...] it's much easier to fine-tune a "general" model into performing some very specific custom task (like classifying text, or translation, etc)
Is this fine-tunning process similar to training models? As in, do you need exhaustive resources? Or can this be done (realistically) on a consumer-grade GPU?
Can you please elaborate what you mean by "critical market"?
Edit: formatting