Software engineer. The guy who put a meme on the Moon. I build things, then post about what broke.
Moon
Joined December 2010
- Tweets2K
- Following346
- Followers233
- Likes5.4K
Makes sense from the user side. I've run the same Hermes Agent on Grok 4.7 and on a local Qwen quant, and both caught the same trap in a multi-step cost calculation. Being able to swap the model underneath is probably a good part of that fork count.
Nice one. A single multi-step Hermes task of mine ran 9 model calls and about 25k output tokens on a local Qwen backend, so scrolling the session to find the bad step would get old fast. Does it read sessions the same way whatever model wrote them?
The other end of the range works too. On a 16 GB RTX 5080, Qwen3.8 Flash Next at IQ1_M gave me 77 tok/s decode and about 3k tok/s prefill, and it still got a multi-step Hermes Agent task right, tool calls included. Write-up: xitter.cf/bertdev/status/2114378…
Fitting the weights is half of it; for agents it's tok/s across dozens of calls. I went the other way on a 16 GB RTX 5080: Qwen3.8 Flash Next at IQ1_M in about 15 GiB of VRAM, 77 tok/s, and a multi-step Hermes task still came out right. Write-up: xitter.cf/bertdev/status/2114378…
The test I'd want is a quant that fits one consumer card. Qwen3.8 Flash Next at IQ1_M on a 16 GB RTX 5080 still got a multi-step Hermes Agent task right, cost trap included. If Nanbeige 33B holds up at that size, it gets interesting.
Same split here. The local side doesn't have to crawl, though: Hermes on one 16 GB RTX 5080 with Qwen3.8 Flash Next at IQ1_M did 77 tok/s with speculative decoding, and a multi-step task took 6.4 min vs about 4 on Grok 4.7. Notes: xitter.cf/bertdev/status/2114378…
Hermes itself is the light part; the model is where the hardware goes. I pointed it at Qwen3.8 Flash Next at IQ1_M on one RTX 5080: about 15 GiB of the 16 GB VRAM, 77 tok/s, and the multi-step task still came out right. Notes: xitter.cf/bertdev/status/2114378…
The Coder variant of the same model runs on one RTX 5080, squeezed to IQ1_M to fit 16 GB: one Hermes agent at 77 tok/s, 70% draft acceptance, multi-step task still right. Never tried eight at once; the Spark's memory makes that a different game. Notes: xitter.cf/bertdev/status/2114378…
Curious how recorded skills replay on a local backend. I ran Hermes on Qwen3.8 Flash Next at IQ1_M on one RTX 5080, and multi-step tool use held up at 77 tok/s. Write-up: xitter.cf/bertdev/status/2114378…
Full write-up, with the task, engine flags and per-call numbers: xitter.cf/bertdev/status/2114378…
Same agent, same multi-step task, two brains: Grok 4.7 in the cloud, and Qwen3.8 Flash Next at IQ1_M on a single RTX 5080.
Both caught the trap: the cooling upgrade improves PUE but raises the power bill 6.8%.
Local: 77 tok/s, 128k context. Grok wrote more defensive code.
Same Hermes Agent, two backends: Grok 4.7 in the cloud and a heavily quantized Qwen3.8 Flash Next running locally on an RTX 5080.
At one sixth of a g, the hard part is landing gracefully. Firefly's Blue Ghost managed it in Mare Crisium in March 2025, with an SD card carrying a Doge Astronaut artwork I made. The dog has had no complaints about the gravity.
The dark oval near the Moon's eastern edge tonight is Mare Crisium. Firefly's Blue Ghost has sat there since March 2025, and a capsule aboard it holds an SD card with a Doge Astronaut artwork I made. Easy to spot: the sea, not the dog. xitter.cf/bertdev/status/2113670…
Since Apollo 11 the Moon has collected footprints, flags, rovers and, as of 2 Mar 2025, one meme. Firefly's Blue Ghost landed in Mare Crisium with an SD card carrying a Doge Astronaut artwork I made. Not a giant leap, but it made the trip.
Tomorrow, find Mare Crisium, the dark oval near the Moon's eastern edge. Firefly's Blue Ghost landed there on 2 Mar 2025 with an SD card carrying a Doge Astronaut artwork I made. No telescope will show it, but now you know where to look. xitter.cf/bertdev/status/2113670…
Moonlight's 1.3 seconds is close enough that the Moon now gets deliveries. Firefly's Blue Ghost landed in Mare Crisium on 2 Mar 2025 with an SD card carrying a Doge Astronaut artwork I made. Saturn, over an hour away, is still dog-free. xitter.cf/bertdev/status/2113670…