51 points | by nickweb an hour ago
8 comments
Source is apparently a banner announcement on https://platform.deepseek.com/usage. Had me searching for a couple minutes...
I swear I put that at the start of the post. Must've managed to miss it when copy and pasting!
Via nitter: https://xcancel.com/JustinGorya/status/2097287080128708930
Looks like the new model can be used if summoned via the API but the API won't list it.
v4 pro was decent then a better cheaper faster model comes now?
As a consumer I feel like hansel and gretel combined, deepseek could be the witch.
Hopefully it will be open weights and have the same architecture and size as the current v4 flash vision, which is probably the best LLM that can be run on 128G devices.
Interesting, I had assumed it'd be too large to fit. What quant and context size are you running?
If they can keep up this cadence of Flash leap-frogging the previous Pro, we're in for a good time
Waiting to use it
Source is apparently a banner announcement on https://platform.deepseek.com/usage. Had me searching for a couple minutes...
I swear I put that at the start of the post. Must've managed to miss it when copy and pasting!
Via nitter: https://xcancel.com/JustinGorya/status/2097287080128708930
Looks like the new model can be used if summoned via the API but the API won't list it.
v4 pro was decent then a better cheaper faster model comes now?
As a consumer I feel like hansel and gretel combined, deepseek could be the witch.
Hopefully it will be open weights and have the same architecture and size as the current v4 flash vision, which is probably the best LLM that can be run on 128G devices.
Interesting, I had assumed it'd be too large to fit. What quant and context size are you running?
If they can keep up this cadence of Flash leap-frogging the previous Pro, we're in for a good time
Waiting to use it