Like this Codex Cli reviewing all thermals of the DGX Sparks cluster by SSHing into them from my MacBook
@theahmadosman
-
Tensor Parallelism multiplies bandwidth for faster tokens in stacked GPUs
By
–
Tensor Parallelism is a bandwidth multiplier btw That’s why stacking Mac Studios / DGX Sparks / GPUs increases tokens/second (The rate at which the bandwidth is multiplied is what differentiates Unified Memory from VRAM as well)
-
Best entry point local LLMs punch above weight low hardware
By
–
To clarify, I never said they were equal (I also believe that local will eventually get there, but that’s different story) These 2 models are the current best entry point for people interested in local LLMs, they punch above their weight w/ relatively low hardware requirements.
-
Maximize Single GPU Power with Qwen 3.5 and Gemma 4
By
–
You don’t need Mythos, just learn how to use Qwen 3.5 27B and Gemma 4 31B and you’ll realize you have so much intelligence under your control on a single GPU
-
GLM-5.1 weights open-source, beats top AI models on SWE-Bench
By
–
INCREDIBLE GLM-5.1 weights are now opensource > i’ve had early access to the weights for the past few days
> and yeah… this one matters a lot benchmarks? > SWE-Bench Pro: 58.4
> beats Opus 4.6 (57.3)
> beats GPT-5.4 (57.7)
> beats Gemini 3.1 Pro (54.2) let that sink in -
AI agent fully deploys GPU inference server via Discord
By
–
I let Codex CLI drive the whole thing from spinning up a fresh VM on a Proxmox node
to passing through the GPU & updating drivers to setting up Hermes + llama.cpp inference
and putting the model online to giving me access through Discord Amazing what agents can do for us now -
Hermes with Discord on a local 3070 VM Qwen 3.5 not on bingo card
By
–
Hermes w/ Discord on a local Qwen 3.5 9B (Unsloth UD-IQ3_XXS) running on an unused 3070 VM I used for game streaming via Moonlight back in the day was not on my bingo card for 2026
-
Reminder: Prepare to Sell Kidneys for GPUs
By
–
person X is asking about biology and chemistry
— Ahmad (@TheAhmadOsman) 1 avril 2026
> he's building a biochemical weapn pic.twitter.com/TDJrT83Mh9person X is asking about biology and chemistry > he's building a biochemical weapn
-
RTX PRO 6000 Giveaway Announcement and FAQ
By
–
I am behind, I know… Sorry have a lot going on, it will be sent before end of the week
-
Correction on ICML Submission Numbers: Abstracts vs. Submissions
By
–
is Anthropic gonna opensource this or are we going to have to wait until their next leak? https://t.co/QjoEDRnHZH
— Ahmad (@TheAhmadOsman) 1 avril 2026is Anthropic gonna opensource this or are we going to have to wait until their next leak?