Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

.DeepSeek-V4-Pro-0813 is live on DigitalOcean Serverless Inference and Inference Router. 🚀 1.6T params / 49B active, 1M-token context, AA Intelligence Index of 53 at max reasoning effort.

digitalocean's profile picture

DigitalOcean

222,713 subscribers

347,944 görüntüleme • 2 ay önce •via X (Twitter)

Haberler & PolitikaBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

5 Yorum

Bob Tong profil fotoğrafı
Bob Tong2 ay önce

@deepseek_ai index 53 vs the open-weight median of 27 is a genuinely wide gap, not marginal. worth checking if that holds at lower reasoning effort though, AA's number is explicitly "max reasoning effort" which usually means slower/pricier in practice than the headline suggests

RAZA | AI EXPLORER profil fotoğrafı
RAZA | AI EXPLORER2 ay önce

@deepseek_ai DeepSeek V4 Pro is live on DigitalOcean. 1.6T params, 49B active, and 1M-token context.

Rao Umair profil fotoğrafı
Rao Umair2 ay önce

@deepseek_ai 1.6T parameters with 49B active and a 1M-token context window is a massive setup. DeepSeek V4 Pro looks built for serious workloads.

WhiteCap Data profil fotoğrafı
WhiteCap Data2 ay önce

@deepseek_ai Serverless inference cant reach the data it needs to reason about if your POS, CRM, and email systems stay isolated.

MoExperts profil fotoğrafı
MoExperts2 ay önce

@deepseek_ai curious how this performs on real workloads vs the benchmark claims

Benzer Videolar

.Kimi.ai K3 from Moonshot AI is now live on DigitalOcean Inference Engine. 1M-token context, native vision, built to run agentic tasks for hours. Supported on Inference Router and model synthesis to maximize intelligence per dollar. No setup, no model ops.
0:36

.Kimi.ai K3 from Moonshot AI is now live on DigitalOcean Inference Engine. 1M-token context, native vision, built to run agentic tasks for hours. Supported on Inference Router and model synthesis to maximize intelligence per dollar. No setup, no model ops.

DigitalOcean

671,991 görüntüleme • 3 ay önce

.Grok Build is on DigitalOcean Marketplace. 🆕☁️🤖 SSH in. Run grok. Build. @xAI's coding agent, pre-configured on DigitalOcean Serverless Inference.
0:38

.Grok Build is on DigitalOcean Marketplace. 🆕☁️🤖 SSH in. Run grok. Build. @xAI's coding agent, pre-configured on DigitalOcean Serverless Inference.

DigitalOcean

811,156 görüntüleme • 4 ay önce

Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨
0:28

Treating every inference request the same is lighting money on fire. DigitalOcean Inference Router sends each request to the right model automatically–lower cost, faster response, and no quality tradeoff. Open-source engine. Drop-in API. Live since April. ✨

DigitalOcean

595,422 görüntüleme • 4 ay önce

Among the fastest DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B inference in the market, per Artificial Analysis benchmarks (April 2026). ⚡️🤖 Sub-1-second TTFT. 230 tokens per second. Co-designed every layer of the stack with Inferact, performance optimized vLLM, all on NVIDIA HGX B300. Live on DigitalOcean Serverless Inference now. Full breakdown in the comments. ⬇️
0:25

Among the fastest DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B inference in the market, per Artificial Analysis benchmarks (April 2026). ⚡️🤖 Sub-1-second TTFT. 230 tokens per second. Co-designed every layer of the stack with Inferact, performance optimized vLLM, all on NVIDIA HGX B300. Live on DigitalOcean Serverless Inference now. Full breakdown in the comments. ⬇️

DigitalOcean

39,063 görüntüleme • 6 ay önce

.RadixArk brought DeepSeek V4 to production with DigitalOcean and AMD. AMD Instinct™ MI350X GPU Droplets, plus joint engineering that drove a ~10x throughput gain. When the team that builds the inference engine picks your stack, that's the signal.
0:42

.RadixArk brought DeepSeek V4 to production with DigitalOcean and AMD. AMD Instinct™ MI350X GPU Droplets, plus joint engineering that drove a ~10x throughput gain. When the team that builds the inference engine picks your stack, that's the signal.

DigitalOcean

13,868 görüntüleme • 3 ay önce

From POC to production inference. 🤖🌁 Join us at #DOdeploy in San Francisco where we'll discuss inference-first architectures, predictable inference economics, operational simplicity at scale, & more.
0:26

From POC to production inference. 🤖🌁 Join us at #DOdeploy in San Francisco where we'll discuss inference-first architectures, predictable inference economics, operational simplicity at scale, & more.

DigitalOcean

12,195 görüntüleme • 8 ay önce

Initial DeepSeek v4 and v4 Flash support added to anemll-flash-llama.cpp! 🚀 M5 MAX 128GB can run full DeepSeek-V4 with 1.6T params in original FP8/FP4 weights from SSD without requantization! One-click scripts to convert HF safetensors to dense + MoE sidecar (no GGUF needed) Inference and server examples Prefill and decoding benchmarks Branch and docs here: This is WIP and I plan to add cleanup and more testing this week. Feedback welcome!
0:21

Initial DeepSeek v4 and v4 Flash support added to anemll-flash-llama.cpp! 🚀 M5 MAX 128GB can run full DeepSeek-V4 with 1.6T params in original FP8/FP4 weights from SSD without requantization! One-click scripts to convert HF safetensors to dense + MoE sidecar (no GGUF needed) Inference and server examples Prefill and decoding benchmarks Branch and docs here: This is WIP and I plan to add cleanup and more testing this week. Feedback welcome!

Anemll

32,250 görüntüleme • 6 ay önce

Stop overpaying for every LLM call. 💸 The DigitalOcean Inference Router resolves intent in ~200ms and beats GPT-5.1 and Claude Sonnet 4.5 on routing accuracy. Powered by Rust, WASM, and purpose-built SLMs, it adds milliseconds, not seconds, to every request. 🌊
0:40

Stop overpaying for every LLM call. 💸 The DigitalOcean Inference Router resolves intent in ~200ms and beats GPT-5.1 and Claude Sonnet 4.5 on routing accuracy. Powered by Rust, WASM, and purpose-built SLMs, it adds milliseconds, not seconds, to every request. 🌊

DigitalOcean

19,853 görüntüleme • 5 ay önce

DigitalOcean Inference Router is now available through OpenCode & setup is 3 steps. ☁️🆕🤝 Run/connect & it automatically routes to the right model for the job. No more paying frontier prices for a commit message.
0:33

DigitalOcean Inference Router is now available through OpenCode & setup is 3 steps. ☁️🆕🤝 Run/connect & it automatically routes to the right model for the job. No more paying frontier prices for a commit message.

DigitalOcean

20,992 görüntüleme • 5 ay önce

New on DigitalOcean's Inference Engine: GLM-5.3-Flash from Z.ai. Agentic coding that rivals top-tier models, now natively multimodal for browser and computer use. 1M token context, MoE architecture, one endpoint swap to try it. Senior Developer Advocate Ryan O'Connor breaks it down, and Z.ai for Startups is there to help AI startups build faster with GLM models. 👇
1:10

New on DigitalOcean's Inference Engine: GLM-5.3-Flash from Z.ai. Agentic coding that rivals top-tier models, now natively multimodal for browser and computer use. 1M token context, MoE architecture, one endpoint swap to try it. Senior Developer Advocate Ryan O'Connor breaks it down, and Z.ai for Startups is there to help AI startups build faster with GLM models. 👇

DigitalOcean

140,776 görüntüleme • 1 ay önce

DigitalOcean’s model synthesis tool is now available in public preview. 🆕 A new server-side tool: run multiple models on one inference request and get a single synthesized response, no custom orchestration. Just add it to your existing inference request.
3:22

DigitalOcean’s model synthesis tool is now available in public preview. 🆕 A new server-side tool: run multiple models on one inference request and get a single synthesized response, no custom orchestration. Just add it to your existing inference request.

DigitalOcean

2,192,364 görüntüleme • 3 ay önce

Surprisingly, DeepSeek V4 Flash 0731 beats the Pro 0813 at canvas coding.
0:35

Surprisingly, DeepSeek V4 Flash 0731 beats the Pro 0813 at canvas coding.

stevibe

54,487 görüntüleme • 2 ay önce

.AMD Instinct™ MI350X GPU Droplets are live on DigitalOcean's Agentic Inference Cloud. 🆕 Lower latency. Higher throughput. ✅ Transparent pricing and production-ready scale. ✅ AI without the infrastructure headache. 💯
0:22

.AMD Instinct™ MI350X GPU Droplets are live on DigitalOcean's Agentic Inference Cloud. 🆕 Lower latency. Higher throughput. ✅ Transparent pricing and production-ready scale. ✅ AI without the infrastructure headache. 💯

DigitalOcean

25,539 görüntüleme • 8 ay önce

Stop prototyping, start deploying. ☁️🤖 Join us at #DOdeploy SF to master production #AI inference. Grounded in real-world costs & reliability, we'll show you how to scale with DigitalOcean. 🌁
0:25

Stop prototyping, start deploying. ☁️🤖 Join us at #DOdeploy SF to master production #AI inference. Grounded in real-world costs & reliability, we'll show you how to scale with DigitalOcean. 🌁

DigitalOcean

10,326 görüntüleme • 8 ay önce

LingBot-Video is out on Hugging Face MoE-based video foundation model built for embodied intelligence 30B params, only 3B active at inference Augmented with 70K hours of embodied data on top of large-scale internet video pretraining
1:02

LingBot-Video is out on Hugging Face MoE-based video foundation model built for embodied intelligence 30B params, only 3B active at inference Augmented with 70K hours of embodied data on top of large-scale internet video pretraining

AK

40,846 görüntüleme • 3 ay önce

“Owning your intelligence is owning your future.” Lucas Atkins, CTO of Arcee.ai, on open weights and everything built on top of them. Open Intelligence Summit keynote streams live Oct 13:
1:00

“Owning your intelligence is owning your future.” Lucas Atkins, CTO of Arcee.ai, on open weights and everything built on top of them. Open Intelligence Summit keynote streams live Oct 13:

DigitalOcean

602,447 görüntüleme • 21 gün önce

I can't believe this works, but I got DeepSeek-V4-Flash (284B params) running on a Raspberry Pi 5 (8GB edition) at >1tok/s @ ~8W during full-tilt inference! It uses an untouched copy of antirez's GGUF. Took 160+ experiments over 5 days between GPT-5.5 xhigh and Opus 4.8 max.
0:32

I can't believe this works, but I got DeepSeek-V4-Flash (284B params) running on a Raspberry Pi 5 (8GB edition) at >1tok/s @ ~8W during full-tilt inference! It uses an untouched copy of antirez's GGUF. Took 160+ experiments over 5 days between GPT-5.5 xhigh and Opus 4.8 max.

Dan Woods

185,556 görüntüleme • 5 ay önce

DeepSeek Harness 能拯救这次 V4-Pro 的发布吗? 给大家带来 DeepSeek-V4-Pro-0813 实测! 本期视频我们只验证4件事: deepseek-v4-pro-0813 拉了吗? v4-pro 推理强度 max 甚至不如 high 吗? 甚至打不过 v4-flash 吗? 以及 v4-pro + deepseek harness 效果会更好吗? 视频告诉你答案! #deepseek #deepseekv4pro #deepseekv4pro0813
6:45

DeepSeek Harness 能拯救这次 V4-Pro 的发布吗? 给大家带来 DeepSeek-V4-Pro-0813 实测! 本期视频我们只验证4件事: deepseek-v4-pro-0813 拉了吗? v4-pro 推理强度 max 甚至不如 high 吗? 甚至打不过 v4-flash 吗? 以及 v4-pro + deepseek harness 效果会更好吗? 视频告诉你答案! #deepseek #deepseekv4pro #deepseekv4pro0813

karminski-牙医

79,888 görüntüleme • 2 ay önce

I mapped the labs' free tiers in the article. These platforms made free access a daily habit, not a one-time trial: > TokenRouter: Qwen3.8-Max at $0. Kimi K3 and paid Qwen3.8-Max at 50% off: > OpenRouter: Ox Alpha (1M context, reasoning + coding) and Dots3-Note Preview (512K context, MoE 280B). Both free: > OrcaRouter: DeepSeek V4 Flash, DeepSeek V4 Pro, Qwen3.8 27B, Tencent HY3. All $0/token, no card, no trial timer. Plus active voucher campaigns: 60% deposit match up to $500: > ZenMux: GLM 5.3 (1M context), DeepSeek V4 Flash Vision, GLM 4.7 Flash, GLM 4.6V Flash multimodal, Agnes-2.5-Flash, Ling-3.0-tiny. All free: > ZarkLab: for video and image creators. Starter plan is $0 forever (1,500 credits, ~187 images + ~4 videos). Creator and Pro: first month free, then $10/$30: > ChatGPT Plus: periodically drops promo codes through partners and marketing campaigns. No public referral link. Catch them when they appear: Frontier access at $0 is no longer a launch promo. It's a standing offer.
0:28

I mapped the labs' free tiers in the article. These platforms made free access a daily habit, not a one-time trial: > TokenRouter: Qwen3.8-Max at $0. Kimi K3 and paid Qwen3.8-Max at 50% off: > OpenRouter: Ox Alpha (1M context, reasoning + coding) and Dots3-Note Preview (512K context, MoE 280B). Both free: > OrcaRouter: DeepSeek V4 Flash, DeepSeek V4 Pro, Qwen3.8 27B, Tencent HY3. All $0/token, no card, no trial timer. Plus active voucher campaigns: 60% deposit match up to $500: > ZenMux: GLM 5.3 (1M context), DeepSeek V4 Flash Vision, GLM 4.7 Flash, GLM 4.6V Flash multimodal, Agnes-2.5-Flash, Ling-3.0-tiny. All free: > ZarkLab: for video and image creators. Starter plan is $0 forever (1,500 credits, ~187 images + ~4 videos). Creator and Pro: first month free, then $10/$30: > ChatGPT Plus: periodically drops promo codes through partners and marketing campaigns. No public referral link. Catch them when they appear: Frontier access at $0 is no longer a launch promo. It's a standing offer.

ＺＥＦＩ

10,256 görüntüleme • 2 ay önce