| NVIDIA Nemotron 3 Nano Omni is now available on Clarifai with Zero Day support.
A 30B A3B multimodal reasoning model b… |
@clarifai |
Company |
Original |
2026-04-28 |
2,312 |
13 |
4 |
2 |
0 |
2 |
| Qwen3.6-35B-A3B is now live on Clarifai. 🚀
The model delivers frontier-level agentic coding performance with a MoE arc… |
@clarifai |
Company |
Original |
2026-04-17 |
567 |
4 |
0 |
1 |
0 |
0 |
| Clarifai 12.3: Introducing KV Cache-Aware Routing! 🚀
LLM inference with multiple replicas typically uses random load b… |
@clarifai |
Company |
Original |
2026-04-10 |
325 |
4 |
1 |
0 |
0 |
0 |
| Do you feel the need for speed?
Come learn how Clarifai breaks speed records for inference across multiple models at B… |
@clarifai |
Company |
Quote |
2026-04-07 |
737 |
4 |
3 |
1 |
1 |
0 |
| Day 1 at HumanX! 🚀
Clarifai is at booth #405 showing how we're running reasoning models in production.
We hit 500+ TP… |
@clarifai |
Company |
Original |
2026-04-06 |
210 |
4 |
1 |
0 |
0 |
0 |
| Vendor lock-in is the biggest AI infrastructure risk nobody's planning for.
The attempted federal ban on Anthropic in … |
@clarifai |
Company |
Original |
2026-04-01 |
281 |
2 |
2 |
0 |
0 |
0 |
| Clarifai is heading to HumanX 2026 in San Francisco. 🚀
At GTC this week, we announced 414 tokens per second on Kimi K2… |
@clarifai |
Company |
Original |
2026-03-25 |
365 |
3 |
0 |
0 |
0 |
0 |
| Day 3 for GTC is here and there is a new pole sitter for Qwen3.5 performance.
Clarifai Reasoning Engine approaches 300… |
@clarifai |
Company |
Original |
2026-03-18 |
234 |
2 |
2 |
2 |
0 |
0 |
| Day 2 at GTC. 🚀
Clarifai Reasoning Engine hit 410 tokens per second on Kimi K2.5, making us one of the first providers… |
@clarifai |
Company |
Original |
2026-03-17 |
281 |
3 |
0 |
1 |
0 |
0 |
| 👀
What company broke the 400 token per second barrier on @Kimi_Moonshot K2.5 first?
Check out Clarifai in Jensen's @n… |
@clarifai |
Company |
Original |
2026-03-16 |
8,327 |
15 |
1 |
1 |
3 |
2 |
| Clarifai 12.2: Three-Command CLI Workflow for Model Deployment! 🚀
Model deployment shouldn't require juggling multiple… |
@clarifai |
Company |
Original |
2026-03-12 |
189 |
3 |
1 |
1 |
0 |
0 |
| Heading to NVIDIA GTC 2026?
As GenAI moves into production, two challenges keep coming up: GPU scarcity and rising inf… |
@clarifai |
Company |
Original |
2026-03-10 |
442 |
3 |
2 |
0 |
0 |
0 |
| Most MCP servers live in local dev environments.
But real applications need them as stable endpoints.
MCP servers are… |
@clarifai |
Company |
Original |
2026-03-06 |
212 |
4 |
3 |
0 |
0 |
1 |
| Choosing an open-source LLM for production is harder than it looks.
Benchmarks are helpful. But they don’t tell you ho… |
@clarifai |
Company |
Original |
2026-03-03 |
146 |
4 |
0 |
0 |
0 |
0 |
| Clarifai will be at NVIDIA GTC 2026.
As GenAI moves from pilot to production, two pressures are hitting hard:
Rising … |
@clarifai |
Company |
Original |
2026-02-26 |
120 |
2 |
0 |
0 |
0 |
0 |
| MCP servers are easy to run locally.
But running them reliably as shared infrastructure is a different problem.
We wr… |
@clarifai |
Company |
Original |
2026-02-24 |
108 |
2 |
0 |
0 |
0 |
1 |
| Everyone is building agentic AI.
Very few are running it in production.
The model performs.
The demo impresses.
Then … |
@clarifai |
Company |
Original |
2026-02-23 |
160 |
2 |
1 |
1 |
0 |
0 |
| Agentic AI is changing the cost and performance equation of building AI systems.
It’s no longer about a single model o… |
@clarifai |
Company |
Original |
2026-02-18 |
131 |
2 |
0 |
0 |
0 |
1 |
| Production agentic AI requires more than powerful models!
It requires infrastructure that can deploy agents reliably, … |
@clarifai |
Company |
Original |
2026-02-13 |
160 |
2 |
1 |
0 |
0 |
0 |
| GPU shortages are the headline.
But the deeper issue is structural.
AI workloads in 2026 look very different from two… |
@clarifai |
Company |
Original |
2026-02-11 |
188 |
4 |
1 |
2 |
0 |
0 |
| Clarifai featured on Ramp’s Top Software Vendors for February 🚀
Ramp’s ranking is based on real spend and new customer… |
@clarifai |
Company |
Original |
2026-02-05 |
425 |
4 |
1 |
0 |
0 |
0 |
| Why pipelines matter for real AI workloads
Once AI work stops fitting into a single request, things start to break.
T… |
@clarifai |
Company |
Original |
2026-02-03 |
125 |
4 |
1 |
1 |
0 |
0 |
| Billing should not slow down AI work.
Clarifai uses a single Pay-As-You-Go credit system for self-serve usage. One bal… |
@clarifai |
Company |
Original |
2026-01-28 |
168 |
2 |
1 |
1 |
0 |
0 |
| You can now deploy public, open-source MCP servers directly on Clarifai ⚡
Upload an existing MCP server, deploy it onc… |
@clarifai |
Company |
Original |
2026-01-27 |
128 |
2 |
0 |
0 |
0 |
0 |
| 🚀 Model Routing with Multi-Nodepool Deployments
You can now route a single model deployment across multiple nodepools.… |
@clarifai |
Company |
Original |
2026-01-21 |
181 |
6 |
1 |
0 |
0 |
0 |
| H100 vs GH200 for AI workloads!
If you’re compute-bound and fit in GPU memory, H100 is usually the right call.
If mem… |
@clarifai |
Company |
Original |
2026-01-14 |
105 |
3 |
1 |
0 |
0 |
0 |
| AI billing should not be unpredictable.
We heard the same issues from teams building on Clarifai: surprise charges, co… |
@clarifai |
Company |
Original |
2026-01-09 |
126 |
2 |
1 |
0 |
0 |
0 |
| Clarifai now uses a single Pay-As-You-Go credit system for self-serve usage.
One balance across training, inference, w… |
@clarifai |
Company |
Original |
2026-01-06 |
339 |
6 |
3 |
0 |
0 |
1 |
| Many image classification workflows require strict policies, edge-case handling, and consistent decisions at scale.
MM… |
@clarifai |
Company |
Original |
2026-01-02 |
149 |
2 |
0 |
0 |
0 |
0 |
