Comment by locusofself 1 month ago Are there local models that are anywhere near as good at coding as opus 4.6? 5 comments locusofself Reply jasonjmcghee 1 month ago People will insist otherwise, but I haven't seen anything close to sonnet 4.6 that can be run locally. Incipient 1 month ago I don't think anyone can honestly say a huge frontier model is actually going to be matched by something running on 64gb locally? jasonjmcghee 1 month ago I have read many comments saying Qwen3.5 various ~30B models, Gemma 4 ~30B models and now Qwen3.6 "better than sonnet".I don't know how large sonnet and opus are but the rumor is 1T and 5T respectively. urig 1 month ago You don't have to use the most recent bleeding edge model to succeed. A local FOSS coding agent coupled with a reasonably priced LLM could yield the optimal ROI. kadoban 1 month ago Not really. Qwen 3.5 and Gemma and a couple of others are quite good though, and the quants are _very_ runnable on a good gpu.
jasonjmcghee 1 month ago People will insist otherwise, but I haven't seen anything close to sonnet 4.6 that can be run locally. Incipient 1 month ago I don't think anyone can honestly say a huge frontier model is actually going to be matched by something running on 64gb locally? jasonjmcghee 1 month ago I have read many comments saying Qwen3.5 various ~30B models, Gemma 4 ~30B models and now Qwen3.6 "better than sonnet".I don't know how large sonnet and opus are but the rumor is 1T and 5T respectively. urig 1 month ago You don't have to use the most recent bleeding edge model to succeed. A local FOSS coding agent coupled with a reasonably priced LLM could yield the optimal ROI.
Incipient 1 month ago I don't think anyone can honestly say a huge frontier model is actually going to be matched by something running on 64gb locally? jasonjmcghee 1 month ago I have read many comments saying Qwen3.5 various ~30B models, Gemma 4 ~30B models and now Qwen3.6 "better than sonnet".I don't know how large sonnet and opus are but the rumor is 1T and 5T respectively. urig 1 month ago You don't have to use the most recent bleeding edge model to succeed. A local FOSS coding agent coupled with a reasonably priced LLM could yield the optimal ROI.
jasonjmcghee 1 month ago I have read many comments saying Qwen3.5 various ~30B models, Gemma 4 ~30B models and now Qwen3.6 "better than sonnet".I don't know how large sonnet and opus are but the rumor is 1T and 5T respectively.
urig 1 month ago You don't have to use the most recent bleeding edge model to succeed. A local FOSS coding agent coupled with a reasonably priced LLM could yield the optimal ROI.
kadoban 1 month ago Not really. Qwen 3.5 and Gemma and a couple of others are quite good though, and the quants are _very_ runnable on a good gpu.
People will insist otherwise, but I haven't seen anything close to sonnet 4.6 that can be run locally.
I don't think anyone can honestly say a huge frontier model is actually going to be matched by something running on 64gb locally?
I have read many comments saying Qwen3.5 various ~30B models, Gemma 4 ~30B models and now Qwen3.6 "better than sonnet".
I don't know how large sonnet and opus are but the rumor is 1T and 5T respectively.
You don't have to use the most recent bleeding edge model to succeed. A local FOSS coding agent coupled with a reasonably priced LLM could yield the optimal ROI.
Not really. Qwen 3.5 and Gemma and a couple of others are quite good though, and the quants are _very_ runnable on a good gpu.