Run a 763B-parameter model locally. DeepSeek-V4.1-Flash-1017 on a 12GB GPU.
Frontier quality with GSQ-RCO quants, directly supported in the Strata inference engine.
Further info below. Much more to come. Follow for updates.
763B parameters, compressed to 1 bit per weight.
Introducing DeepSeek-V4.1-Flash-1017 GSQ-RCO Coder, a frontier-scale model tailored for coding and agentic workflows.
Benchmarks, demos and download link below. Follow us for updates.
We have noticed recent comparisons published by Unsloth that do not align with our results for DeepSeek-V4.1-Flash-1017. So just if it is not obvious: we did of course not modify any hyperparameters to favor our models. We used standard settings appropriate for a model of this
I couldn't agree more!
Kld is only used to evaluate quantized models because it's very cheap.
It was not designed for LLM eval. And most GGUF users, who dont have any ml background, have no idea what it means and over interpret it
Still good for quick diagnostic purposes