I didn’t read the article but I will say that the value/performance of Deepseek v4 flash is so awesome it is a lifesaver and I’m thrilled for it.
DeepSeek V4: The Open-Source Model Frontier Labs Feared
21–30 of 36 posts
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#22[dead]
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#23Earlier quoted context omitted.
Is there a good 4th option yet? I haven't really been impressed by what I've tried so far. I believe Claude Code only works with claude and seems all I hear about that is it's great but the token limits are so anemic as to make it useless unless you want to shell out $200+ a month, which I do not so I haven't bothered. I tried codex but it wouldn't run out-of-the-box. Installation on a fresh Windows box resulted in s…
>I believe Claude Code only works with claude and seems all I hear about that is it's great but the token limits are so anemic as to make it useless unless you want to shell out $200+ a month, which I do not so I haven't bothered. I use Claude Code with GLM 5.q, Kimi K2.6, MiniMax M2.7 and Xiaomi MiMo V2.5 Pro.
ah , wasn't aware it was open for use with non Claude models I'll take a closer look at it then. thanks.
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#24Do you know what kind of machine do I need to run the original DeepSeek v4 pro model with a good tok/s throughput?
You don't need a machine. You need a rack of them. 1.34TB VRAM https://wavespeed.ai/blog/posts/deepseek-v4-gpu-vram-require...
less if you quantize. apparently Q8 and Q4 do pretty well.
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#25In my personal experience, no model comes close to claude when it comes to coding performance. It does not matter what any of the benchmarks says. Having said that I really hope this model of deepseek, performs significantly on par with the claude saunnet model.
It's also 28 times more expensive than V4 pro and 111 times than V4 Flash.
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#26Do you know what kind of machine do I need to run the original DeepSeek v4 pro model with a good tok/s throughput?
You don't need a machine. You need a rack of them. 1.34TB VRAM https://wavespeed.ai/blog/posts/deepseek-v4-gpu-vram-require...
Nobody is serving models in BF16 precision, not even commercial providers. Especially with newer quant methods (like nv4)
The article states you can fit Q4 in 4 x 4090 and it works reasonably well.
I'd personally fo for deepseek V4 flash at Q8, hardware prices need to come down though. Once an NV4 version get released it'll be easier to run on commodity hardware.
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#27Earlier quoted context omitted.
Is there a good 4th option yet? I haven't really been impressed by what I've tried so far. I believe Claude Code only works with claude and seems all I hear about that is it's great but the token limits are so anemic as to make it useless unless you want to shell out $200+ a month, which I do not so I haven't bothered. I tried codex but it wouldn't run out-of-the-box. Installation on a fresh Windows box resulted in s…
>I believe Claude Code only works with claude and seems all I hear about that is it's great but the token limits are so anemic as to make it useless unless you want to shell out $200+ a month, which I do not so I haven't bothered. I use Claude Code with GLM 5.q, Kimi K2.6, MiniMax M2.7 and Xiaomi MiMo V2.5 Pro.
Why use Claude Code over something like Opencode then? From my limited usage of the tools over the past couple of months Claude Codes ergonomics feel strictly worse than Opencode, but I haven't deeply investigated either yet. I am using Claude models in both so I am getting a one to one comparison.
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#28Earlier quoted context omitted.
>I believe Claude Code only works with claude and seems all I hear about that is it's great but the token limits are so anemic as to make it useless unless you want to shell out $200+ a month, which I do not so I haven't bothered. I use Claude Code with GLM 5.q, Kimi K2.6, MiniMax M2.7 and Xiaomi MiMo V2.5 Pro.
Why use Claude Code over something like Opencode then? From my limited usage of the tools over the past couple of months Claude Codes ergonomics feel strictly worse than Opencode, but I haven't deeply investigated either yet. I am using Claude models in both so I am getting a one to one comparison.
Because I tried OpenCode and Claude Code seems a better harness. It has the best plugins and many skills are designed to work best with Claude Code.
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#29Am I able to play with it at home?
Re: DeepSeek V4: The Open-Source Model Frontier Labs Feared
#30I didn’t read the article but I will say that the value/performance of Deepseek v4 flash is so awesome it is a lifesaver and I’m thrilled for it.
deepseek v4 flash is basically the anthropic killer. I've been able to offload the vast majority of my workflow to that using opencode go. between that and the occasional use of pro and kimi k.26, I don't understand what the big deal is about claudecode.