181–190 of 1001 posts
I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…
Where is the GPT 5.5 Pelican?
Earlier quoted context omitted.
Weren't there some frameworks recently released to allow Macs to stream weights from fast SSDs and thus fit way more parameters than what would normally fit in RAM? I have never tried one yet but I am considering trying that for a medium sized model.
I've been calling that the "streaming experts" trick, the key idea is to take advantage of Mixture of Expert models where only a subset of the weights are used for each round of calculations, then load those weights from SSD into RAM for each round. As I understand it if DeepSeek v4 Pro is a 1.6T, 49B active that means you'd need just 49B in memory, so ~100GB at 16 bit or ~50GB at 8bit quantized. v4 Flash is 284B, 13…
Streaming weights from RAM to GPU for decode makes no sense at all because batching requires multiple parallel streams.
Streaming weights from SSD _never_ makes sense because the delta between SSD and RAM is too large. There is no situation where you would not be able to fit a model in RAM and also have useful speeds from SSD.
I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…
This should not be the top comment on every model release post. It's getting tiring.
How can you reasonably try to get near frontier (even at all tps) on hardware you own? Maybe under 5k in cost?
The Flash version is 284B A13B in mixed FP8 / FP4 and the full native precision weights total approximately 154 GB. KV cache is said to take 10% as much space as V3. This looks very accessible for people running "large" local models. It's a nice follow up to the Gemma 4 and Qwen3.5 small local models.
Price is appealing to me. I have been using gemini 3 flash mainly for chat. I may give it a try. input: $0.14/$0.28 (whereas gemini $0.5/$3) Does anyone know why output prices have such a big gap?
Truly open source coming from China. This is heartwarming. I know if the potential ulterior motives.
Earlier quoted context omitted.
Open weight!
Please don't slander the most open AI company in the world. Even more open than some non-profit labs from universities. DeepSeek is famous for publishing everything . They might take a bit to publish source code but it's almost always there. And their papers are extremely pro-social to help the broader open AI community. This is why they struggle getting funded because investors hate openness. And in China they strug…
Looking forward to DeepSeek Coding Plan