Let’s roll a cone… No, not like that! Well shit since you rented the costumes for the day…

Thanks for sharing!

I miss when UI looked more like this.

Looks promising, hope this ends up in an open source process that improved RAG type task.

Ooh yes I can see it now like to a door! I thought it was a belt buckle type thing at first but now I think you got it right. Thank you!!

FromSoft fans who have been around since Kingfield in the late 90s: “always has been” (because from hit gold with the old and decaying fantasy world with dwindling hope in its inhabitants atmospheric vibe and keep reusing it)

This is so exciting! Glad to see mistral at it with more bangers.

Hi Hawke, I understand your fustration with needing to troubleshoot things. Steam allows you to import any exe as a ‘non-steam game’ to your library and run it with the proton compatability layer. I sometimes have success getting a GOG game installed by running the install exe through proton or wine. Make sure you are using the most up to date version of lutris many package managers are outdated flatpak will gaurentee its most up to date. Hope it all works out for you

assuming you use steam, see which of your favorite games run with proton compatability layer and which absolutely require windows. You may be suprised.

Awesome, thank you!

Thank you for the support Sergio! I hope it works out too.

Ive tried official Deepseek qwen 2.5 14b r1 distill and a few unofficial mistrals trained on R1 CoT. They are indeed pretty amazing and I found myself switching between a general purpose model and a thinking model regularly before this released.

DeepHermes is a thinking model family with R1 distill CoT that you can toggle between standard short output or spending a few thousand tokens thinking about a solution.

I found that pure thinking models are fantastic for asking certain kinds of problem solving questions, but awful at following system prompt changes for roleplay scenarios or adopting complex personality archetypes.

This let’s you have your cake and eat it too by letting CoT be optional while keeping regular system prompt capabilities.

The thousands of tokens spent thinking can get time consuming when you only getting 3t/s on the larger 24b models. So its important to choose between a direct answer or spend 5 minutes to let it really think. Its abilities are impressive even if it takes 300 seconds to fully think out a problem at 2.5t/s.

Thats why I am so happy the 8b model is pretty intelligent with CoT enabled so I can fit a thinking model entire in vram and its not dumb as rocks in knowledge base either. I’m getting 15-20t/s with 8b instead of 2.5-3t/s partially offloading a larger model. 6.4x speed inceease at the CoT is a huge W for my real life human time spent waiting for a complete output.

Great question. Sometimes I feel like ive lost the plot of enjoying the human experience. When the majority of the members of my species exhibit a behavior or inpulse that I cant relate to or dont understand, I second guess whether its me missing something fundamental to enjoying my existence or whether Ive overcome a certain flaw most others haven’t or something else.

You are correct though I should be a little more confident in the choices ive made and the rationals of why I made it.

I had planned on traveling in my minivan with a cot and bed for an extended period of time at some point so wanted to make sure I got something I could use in multiple scenarios. Also it was what I could afford at the time within budget. The space and ease of movement are big bonuses to me.

Thanks for providing your perspective and personal insights!

I think the idea of calling multiple different kinds of ways to for llms to ‘process’ a given input in a standard way is promising.

I feel that after reasoning we will train models how to think emotionally in a more intricate way. By combining reasoning with a more advanced sense of individuality and greater emotions simulation we may get a little closer to finding a breakthrough.

A dedicated conviction and multi year effort to improve myself. There is no dirt secret. You either cut calories or exercise to make up a deficit.

Metabolism and nutrients and all that help. I think it mainly boils down to learning how to be more active and live with being hungry for a while sometimes.

I just spent a good few hours optimizing my LLM rig. Disabling the graphical interface to squeeze 150mb of vram from xorg, setting programs cpu niceness to highest priority, tweaking settings to find memory limits.

I was able to increase the token speed by half a second while doubling context size. I don’t have the budget for any big vram upgrade so I’m trying to make the most of what ive got.

I have two desktop computers. One has better ram+CPU+overclocking but worse GPU. The other has better GPU but worse ram, CPU, no overclocking. I’m contemplating whether its worth swapping GPUs to really make the most of available hardware. Its bee years since I took apart a PC and I’m scared of doing somthing wrong and damaging everything. I dunno if its worth the time, effort, and risk for the squeeze.

Otherwise I’m loving my self hosting llm hobby. Ive been very into l learning computers and ML for the past year. Crazy advancements, exciting stuff.

Cool, page assist looks neat I’ll have to check it out sometimes. My llm engine is kobold.cpp, and I just user the openwebui in internet browser to connect.

Sorry I don’t really have good suggestions for you beyond to just try some of the more popular 1-4bs in a very high quant if not full f8 and see which works best for your use case.

Llama 4b, mistral 4b, phi-3-mini, tinyllm 1.5b, qwen 2-1.5b, ect ect. I assume you want a model with large context size and good comprehension skills to summarize youtube transcripts and webpage articles? At least I think thats what the add-on you mentioned suggested was its purpose.

So look for models with those things over ones that try to specialize in a little bit of domain knowledge.

Haha yeah it sure did! Thanks for sharing. I find it funny the first and only example is using a * rope* to pull it away.

Hermes CoT: “no, quantum wormhole wont work either, maybe antimatter propulsion drive. But then again that can’t be…”

NeMo: “Rope. Temperature resistant. I dunno get a big space truck and haul it. You do the math.” taps forehead

The average of all different benchmarks can be thought of as a kind of ‘average intelligence’, though in reality its more of a gradient and vibe type thing.

Many models are “benchmaxxed” trained to answer the exact kinds of questions the test asked which often makes the benchmarks results unrelated to real world use case checks. Use them as general indicators but not to be taken too seriously.

All model families are different in ways that you only really understand by spending time with them. Don’t forget to set the rigt chat template and correct sample range values as needed per model. Openleaderboard is a good place to start.