正在加载视频...

视频加载失败

▲ Marktechpost just launched GPU Leaderboard ( in beta mode), a free cloud GPU price comparison for inference, along with a Chrome extension. The key idea is pricing a whole run, not a single hourly rate. Pick a GPU, count, duration and utilization, and it prices that exact run...

75,282 次观看 • 6 天前 •via X (Twitter)

1 条评论

Jenil Rita 的头像
Jenil Rita6 天前

Pricing the whole run is the right unit. An hourly GPU rate hides how long the job actually sits there.

相关视频

Introducing KausaCompute. Running AI models privately is expensive and complicated. Traditional cloud providers require credit cards, KYC verification, and complex setup processes. For many developers, especially in emerging markets, accessing GPU compute remains out of reach. KausaCompute changes that. Deploy any Docker container with NVIDIA GPU, pay with USDC from Maze Pocket, no KYC, no credit card, no cloud provider account needed. GPU pricing starts at $0.47/hr with competitive rates across all tiers. KausaCompute lives inside KausaLayer Pocket. Open a pocket, swap SOL to USDC using the built-in swap feature, and start deploying GPU containers right away. Everything stays within one ecosystem. What it actually does: Private LLM endpoints. Deploy Llama 3, Mistral, CodeLlama, or any open-source model as a personal API. No one logs the prompts. No one reads the data. Full control. AI coding assistants that never see external servers. Speech-to-text processing for thousands of audio files in minutes instead of hours. Sentiment analysis across millions of data points. Document summarization at scale. Multi-modal AI that processes images and text together. All running on dedicated NVIDIA GPUs. A6000, T4, L4, L40, A100, H100, and more. Pick the hardware, pick the duration, deploy in one click. The billing is straightforward. USDC is deducted from Maze Pocket before deployment. Pro tip: Maze Pocket supports multiple pockets per wallet. Create a dedicated pocket just for KausaCompute to keep GPU spending separate from other activities like trading or transfers. Clean separation, easy tracking. KausaCompute is not another cloud provider. It is the fastest path from USDC to a running GPU, with zero identity requirements. Live now at

KausaLayer

10,967 次观看 • 5 个月前

UC Berkeley just open-sourced FreeToken. (2–4x faster local LLM inference than Ollama) the results are wild: - Qwen3.6-35B on an 8GB GPU at 39.3 tokens/s - DeepSeek-V4-Flash 284B on a 32GB GPU at 22 tokens/s - GLM-5.2 753B on a 96GB GPU at 14.9 tokens/s a 35B model at 16-bit precision needs about 70GB just for its weights. even at 4 bits it is close to 18GB, and FreeToken serves it on an 8GB GPU. let me explain how: all three models mentioned above are Mixture-of-Experts, and that is what FreeToken takes advantage of. each layer holds hundreds of separate experts plus a small router that picks a few of them per token. Qwen3.6-35B activates roughly 3B of its 35B parameters per token. DeepSeek-V4-Flash picks 6 of 256 experts per layer, so 13B of its 284B run at a time. so compute was never the bottleneck. the weights a single step touches fit comfortably on a consumer GPU. every expert the router might pick still has to exist somewhere. they sit in system RAM, and the GPU keeps a cache of the ones the model has been using recently. so everything comes down to what happens when the router picks an expert that is not on the GPU. there are two ways to serve that miss: 1. copy it over PCIe and run it on the GPU 2. run it on the CPU, where it already lives both read from the same system memory, so they compete for one pool of bandwidth instead of adding to each other. existing engines pick one option and freeze it when the model loads. but routing changes on every token, so a fixed choice misses most of what the model asks for. FreeToken measures both bandwidths on your machine and splits each step's misses between the two paths in proportion. the GPU and CPU results then merge exactly, with no approximation. two machines with the same GPU can end up wanting opposite strategies, which I did not expect. a 5090 in a gaming desktop should push nearly everything over PCIe, while an 8GB laptop is better off computing most misses on the CPU. none of that is readable off a spec sheet, so the engine profiles it once per machine. the second half of the design is about agents. coding agents constantly rewrite their own history, and every edit normally forces thousands of tokens back through prefill. FreeToken saves its checkpoints at the exact boundaries agent frameworks cut on, so it only reprocesses the new part. its slowest first token stays under 44 seconds, while llama.cpp peaks at 232 and KTransformers at 946. it serves the OpenAI and Anthropic APIs under Apache 2.0, so Claude Code and Codex can point at it directly. releasing weights publicly decides who can download a model, not who can afford to run one. frontier open models keep shipping, and running them still assumes a rented cluster. meanwhile there are over a hundred million consumer machines with discrete GPUs sitting mostly idle. closing that gap was never a hardware problem, and work like this is what turns open weights into something you can actually use. paper: repo: almost every idea in this post, from why memory bandwidth decides the outcome to why moving weights costs more than computing on them, comes straight out of how a GPU is built. I wrote a detailed primer on that. the article is quoted below.

Akshay 🚀

346,057 次观看 • 2 个月前

Chamath Palihapitiya just dropped the number that explains the entire AI infrastructure trade (Save this). A gigawatt of compute now costs $100 billion and when he started his Arizona data center project it was $4 to $5 billion, it has gone up 20x in a single investment cycle. The implication is not just that AI infrastructure is expensive but rather that the capital barrier to owning meaningful compute has become so high that only a handful of entities in the world can actually build it and the companies who got there early are sitting on what may be the most durable pricing power in the history of the technology industry. This is the neocloud trade. The neocloud market, purpose-built GPU cloud providers like CoreWeave, Nebius, and Lambda Labs was worth $35 billion in 2026 and is projected to reach $236 billion by 2031, compounding at 46% annually. For context, that is faster growth than cloud computing itself posted in its first decade. The reason is very simple, hyperscalers like AWS, Azure, and Google are building for everything, storage, databases, enterprise software, networking and their GPU pricing reflects the overhead of that full-stack infrastructure. Neoclouds build for one thing only, AI compute. The result is a 60% to 85% cost advantage on the same Nvidia silicon, bare metal H100s at $0.78 to $2.79 per GPU-hour on a neocloud versus $3.43 to $5.07 per GPU-hour on a hyperscaler. That spread does not close as AI demand scales but rather it widens, because hyperscalers have to amortize legacy infrastructure and margin expectations that neoclouds do not carry. Gartner projects that by 2030, neoclouds will capture 20% of the $267 billion AI cloud market, and Vultr's own analysis says at least 80% of GPU market share by end of 2026 will be held by a small group of scaled neocloud providers. Now zoom into Nebius specifically, because it is the most interesting publicly traded proxy for this trade. Nebius is the infrastructure arm of the former Yandex Russia's equivalent of Google rebuilt from the ground up after Russia's invasion of Ukraine by Arkady Volozh and relisted on Nasdaq in October 2024. The team that built it already knew how to run internet-scale infrastructure at the lowest possible cost, which is exactly the operational DNA a neocloud requires. In Q1 2026, Nebius reported revenue of $399 million and already generating serious cash on a young business with revenue growing nearly eightfold year-over-year. Then in March 2026, Meta signed a five-year infrastructure agreement with Nebius worth up to $27 billion, $12 billion in committed dedicated GPU capacity deployments beginning early 2027, plus up to $15 billion more tied to Meta purchasing Nebius's unsold third-party capacity. The deal will be executed on one of the first large-scale deployments of Nvidia's Vera Rubin platform, the next-generation architecture after Blackwell making Nebius one of a tiny number of operators in the world with confirmed priority access to the most advanced AI hardware available. Following the contract, Nebius guided to $7 to $9 billion in annualized recurring revenue for 2026 representing 540% year-over-year growth. Chamath Palihapitiya point about the $100 billion capital moat is the bear case for new entrants and the bull case for incumbents. No one can afford to build the next CoreWeave or Nebius from scratch at current hardware and power costs. The companies that are already built, already contracted, and already deploying Nvidia's latest silicon have a moat that compounds with every GPU generation cycle because they get allocations first, they deploy fastest, and their customers re-sign rather than wait for a new operator that does not yet exist. Come join Milk Road Pro for our full breakdown, the complete neocloud competitive landscape, how to think about Nebius's valuation versus CoreWeave and AI entire thesis. Link below.

Milk Road AI

139,047 次观看 • 5 个月前