Rendered at 03:56:29 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
volf_ 10 hours ago [-]
GLM 5.3 and all previous models don't have a vision encoder and can only accept text. Ox-Alpha can accept video and images, so unless Z-ai added a pretty good vision encoder for this model, I don't think so.
My money is on Moonshot and this being Kimi K3.5. The measured tps and latency is in-line with K3's tps and latency from Moonshot.
MiniMax M3.5 is also possible (but the MiniiMax provider is a lot more performant than the lab behind ox-alpha, so less likely).
nylonstrung 8 hours ago [-]
It would be stranger to me that Kimi switched to GLM's tokenizer than that GLM added multimodal like Kimi and Deepseek both did recently
Almondsetat 10 hours ago [-]
DeepSeek literally just came out with the vision-enabled version of Flash v4 which was purely text based. Why would GLM not be able to do the same thing?
volf_ 9 hours ago [-]
It's possible
Bolwin 10 hours ago [-]
Glm had made vision models in the past. Look up GLM 5v.
The only question now is if it's 5.3v, 5.4/5.5 or a dedicated flash/vision model
volf_ 9 hours ago [-]
Yeah. It could be. The Z.ai DC latency is still ~1.2s faster than whomever is serving this model.
My money is on Moonshot and this being Kimi K3.5. The measured tps and latency is in-line with K3's tps and latency from Moonshot.
MiniMax M3.5 is also possible (but the MiniiMax provider is a lot more performant than the lab behind ox-alpha, so less likely).
The only question now is if it's 5.3v, 5.4/5.5 or a dedicated flash/vision model
Ox Alpha
https://news.ycombinator.com/item?id=49381896