| ▲ | anslopic a day ago |
| [flagged] |
|
| ▲ | adastra22 a day ago | parent | next [-] |
| That’s… not how any of this works. Five paragraphs and literally every one is wrong. |
| |
|
| ▲ | hhh a day ago | parent | prev | next [-] |
| this is insanely misleading, you can't run anything close to current chatgpt or gemini on local hardware |
| |
| ▲ | sharms a day ago | parent | next [-] | | I am running GLM 5.3 across 2x DGX Sparks and was doing comparisons and it absolutely can beat Gemini. Yesterday it corrected a poor Fable 5 response even | | |
| ▲ | hhh 21 hours ago | parent [-] | | I should have clarified, you can’t run it on their local hardware, which is a 16gb gpu. Glm-5.3 and k3 are of course near the frontier. |
| |
| ▲ | colingauvin a day ago | parent | prev | next [-] | | GLM 5.3 Flash? Qwen 3.8 Flash Next? I believe those both are as good as the best Gemini, competitive with Terra. | | |
| ▲ | notnullorvoid a day ago | parent [-] | | Yes they are quite good, but are not able to run on a 16GB RX 9070. Quantized Qwen 3.8 Flash Next could maybe run eventually on that card with a highly optimized inference engine that dynamically caches the hottest layer experts. Even then you run into some hard limits. |
| |
| ▲ | NoYouAre a day ago | parent | prev [-] | | [flagged] |
|
|
| ▲ | throwaway314155 a day ago | parent | prev | next [-] |
| > You have good enough hardware to run good models comparable with Gemini and ChatGPT. That is at best misleading and at worst outright misinformation. |
| |
| ▲ | amazingamazing a day ago | parent [-] | | If you have 2TB of VRAM you can’t run one of the big models which are comparable? | | |
| ▲ | adastra22 a day ago | parent [-] | | The post was replying to someone with 16GB. (And also: no, even the best open weight models are not as good as what you can use on your ChatGPT subscription. They’ve gotten a lot better, but not that much better.) | | |
|
|
|
| ▲ | chis a day ago | parent | prev | next [-] |
| what are you smoking |
| |
|
| ▲ | anslopic a day ago | parent | prev [-] |
| [flagged] |
