Rival.io Launches GraphX, Running DeepSeek V4 Flash on Just Eight NVIDIA L4 GPUs
First small-footprint serving claim: a vendor says eight L4 GPUs suffice, without published benchmarks.
3 items · 2 sources · 3 days
Operational story trace
Follow in this browser to see new updates on your Live feed.
Latest change
Hosting provider Lebrel added an uncensored DeepSeek V4.1 Flash on Nov 18 from $0.13 per million input tokens, alongside Alibaba's Qwen4-Max on day one.
This thread is now a pattern across independent third parties running DeepSeek V4 and V4.1 Flash outside DeepSeek's own API, not one event. It began Oct 29 with Rival.io's GraphX claiming Flash serving on eight NVIDIA L4 GPUs, then a lawyer's private server build on Nov 14 fit 80% of V4.1 Flash on an eight-V100 server at 4-bit NVFP4.
Arc
First small-footprint serving claim: a vendor says eight L4 GPUs suffice, without published benchmarks.
Hands-on self-hosting account with the real costs: partial offload, 1TB RAM, and a hardware failure along the way.
Adds a hosted price point and a modified "uncensored" variant from a third-party provider.
First small-footprint serving claim: a vendor says eight L4 GPUs suffice, without published benchmarks.
Hands-on self-hosting account with the real costs: partial offload, 1TB RAM, and a hardware failure along the way.
Adds a hosted price point and a modified "uncensored" variant from a third-party provider.
What to watch — open questions
Storylines are threaded mechanically from the feed: stories that share a distinctive anchor across multiple days and sources. Each item links to its original source. The evidence trace, current state, and open questions are written by the editor routine and refreshed whenever a new beat lands.