/g/ - /lmg/ - Local Models General - Technology


08/21/20	New boards added: /vrpg/, /vmg/, /vst/ and /vm/
05/04/17	New trial board added: /bant/ - International/Random
10/04/16	New board for 4chan Pass users: /vip/ - Very Important Posts
[Hide] [Show All]

Anonymous
/lmg/ - Local Models General 09/21/25(Sun)20:39:43 No.106660311

File: 1745198947072720.jpg (937 KB, 1552x1944)

/lmg/ - Local Models General Anonymous 09/21/25(Sun)20:39:43 No.106660311

/lmg/ - a general dedicated to the discussion and development of local language models.

First Day of Fall Edition

Previous threads: >>106649116 & >>106635936

►News
>(09/17) SongBloom DPO released: https://hf.co/CypressYang/SongBloom/commit/4b8b9deb199fddc48964c851e8458b9269081c24
>(09/17) Magistral Small 1.2 with vision encoder released: https://hf.co/mistralai/Magistral-Small-2509
>(09/16) Ling-flash-2.0 released, with 100B-A6.1B: https://hf.co/inclusionAI/Ling-flash-2.0
>(09/16) Tongyi DeepResearch 30B-A3B released: https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research
>(09/16) VoxCPM 0.5B: Tokenizer-Free TTS released: https://hf.co/openbmb/VoxCPM-0.5B

►News Archive: https://rentry.org/lmg-news-archive
►Glossary: https://rentry.org/lmg-glossary
►Links: https://rentry.org/LocalModelsLinks
►Official /lmg/ card: https://files.catbox.moe/cbclyf.png

►Getting Started
https://rentry.org/lmg-lazy-getting-started-guide
https://rentry.org/lmg-build-guides
https://rentry.org/IsolatedLinuxWebService
https://rentry.org/recommended-models
https://rentry.org/samplers

►Further Learning
https://rentry.org/machine-learning-roadmap
https://rentry.org/llm-training
https://rentry.org/LocalModelsPapers

►Benchmarks
LiveBench: https://livebench.ai
Programming: https://livecodebench.github.io/leaderboard.html
Code Editing: https://aider.chat/docs/leaderboards
Context Length: https://github.com/adobe-research/NoLiMa
GPUs: https://github.com/XiongjieDai/GPU-Benchmarks-on-LLM-Inference

►Tools
Alpha Calculator: https://desmos.com/calculator/ffngla98yc
GGUF VRAM Calculator: https://hf.co/spaces/NyxKrage/LLM-Model-VRAM-Calculator
Sampler Visualizer: https://artefact2.github.io/llm-sampling

►Text Gen. UI, Inference Engines
https://github.com/lmg-anon/mikupad
https://github.com/oobabooga/text-generation-webui
https://github.com/LostRuins/koboldcpp
https://github.com/ggerganov/llama.cpp
https://github.com/theroyallab/tabbyAPI
https://github.com/vllm-project/vllm

Anonymous
09/21/25(Sun)20:40:01 No.106660313

Anonymous 09/21/25(Sun)20:40:01 No.106660313

File: __hatsune_miku_vocaloid_d(...).jpg (699 KB, 2935x2068)

699 KB JPG

►Recent Highlights from the Previous Thread: >>106649116

--Paper: Why Language Models Hallucinate:
>106658640 >106658668 >106658948 >106659053 >106659814
--Qwen models benchmark analysis on Adobe's NoLiMa and blind model visualization critique:
>106654812 >106655221 >106655251 >106655352 >106655599 >106655358 >106655473 >106655503 >106655563 >106655582 >106655641 >106655658 >106655720 >106656651 >106655980 >106656013 >106658871 >106656247 >106656396 >106655048
--Optimizing glm air moe benchmarking with ROCm and thread tuning:
>106656736 >106656807 >106656847 >106656869 >106656945 >106657150 >106657190 >106657225
--Celebrating dots.ocr's superior OCR performance over traditional models:
>106657368 >106657400 >106657603 >106657461 >106657468
--Feasibility debate on iterative LLM training through manual answer corrections:
>106649345 >106649390 >106649419 >106649452 >106659303
--Dense vs MoE model scaling efficiency with increased compute:
>106649319 >106649336 >106653343 >106653422 >106650040
--Dense vs MoE model trade-offs in computational efficiency and informational completeness:
>106655627 >106655749 >106655787
--Measuring AI model power consumption by comparing idle and active server wattage:
>106657883 >106657924 >106658048
--GLM-4.5-FP8 model performance demonstration:
>106657800
--Exploring cognitive architectures vs. task-specific AI agents for practical use:
>106652491 >106652548 >106652716 >106652750
--Using emojis to influence LLM behavior and roleplay consistency:
>106652708 >106652872 >106652979
--Local LLM model size/performance tradeoffs:
>106649199 >106649361 >106649368 >106649381 >106649487 >106649522 >106649681 >106649521 >106649667 >106649684
--koboldcpp-1.99 release announcement:
>106653905
--Miku (free space):
>106649184 >106649223 >106650338 >106650361 >106650425 >106653084 >106653983 >106657883 >106658098

►Recent Highlight Posts from the Previous Thread: >>106649119

Why?: >>102478518
Enable Links: https://rentry.org/lmg-recap-script

Anonymous
09/21/25(Sun)20:43:48 No.106660339

Anonymous 09/21/25(Sun)20:43:48 No.106660339

mikutroon faggots

Anonymous
09/21/25(Sun)20:45:01 No.106660349

Anonymous 09/21/25(Sun)20:45:01 No.106660349

File: bark-like.jpg (7 KB, 772x25)

7 KB JPG

Fucking shit

Anonymous
09/21/25(Sun)20:52:20 No.106660409

Anonymous 09/21/25(Sun)20:52:20 No.106660409

how do i use vLLM

Anonymous
09/21/25(Sun)20:57:17 No.106660452

Anonymous 09/21/25(Sun)20:57:17 No.106660452

WHEN YOU WALK AWAY

YOU DON'T HEAR ME SAY

PLEASE

OH BABY

DON'T GO

Anonymous
09/21/25(Sun)20:59:44 No.106660476

Anonymous 09/21/25(Sun)20:59:44 No.106660476

>>106660349
looks ruff

Anonymous
09/21/25(Sun)21:00:31 No.106660484

Anonymous 09/21/25(Sun)21:00:31 No.106660484

>>106660349
Barely above a woof

Anonymous
09/21/25(Sun)21:02:36 No.106660491

Anonymous 09/21/25(Sun)21:02:36 No.106660491

>>106660349
>bark
If tree bark, that means very rough, and perhaps abrasive like a rasp.

Anonymous
09/21/25(Sun)21:04:00 No.106660502

Anonymous 09/21/25(Sun)21:04:00 No.106660502

>>106660349
we live in a doggy dog world

Anonymous
09/21/25(Sun)21:41:38 No.106660769

Anonymous 09/21/25(Sun)21:41:38 No.106660769

File: 30474 - SoyBooru.png (118 KB, 337x390)

118 KB PNG

Will we get another kiwi in the last 8 days of September?

Anonymous
09/21/25(Sun)22:04:55 No.106660930

Anonymous 09/21/25(Sun)22:04:55 No.106660930

File: what the fuck.png (105 KB, 992x391)

105 KB PNG

Took one of the old cards from back when I lurked aicg and, holy shit GLM, calm the fuck down.
I just asked how was school sheesh.

Anonymous
09/21/25(Sun)22:12:37 No.106660965

Anonymous 09/21/25(Sun)22:12:37 No.106660965

>>106660930
repeated strawberries twice. mid tier model

Q*Anon
09/21/25(Sun)22:13:50 No.106660972

Q*Anon 09/21/25(Sun)22:13:50 No.106660972

File: 21522 - SoyBooru.png (46 KB, 457x694)

46 KB PNG

>>106660930
>strawberries
GLM=AGI

Anonymous
09/21/25(Sun)22:14:03 No.106660973

Anonymous 09/21/25(Sun)22:14:03 No.106660973

guys...I think glm killed my pc...
fuck

Anonymous
09/21/25(Sun)22:15:24 No.106660979

Anonymous 09/21/25(Sun)22:15:24 No.106660979

>>106660973
Agents were a mistake.

Q*Anon
09/21/25(Sun)22:16:37 No.106660988

Q*Anon 09/21/25(Sun)22:16:37 No.106660988

File: strawberry-sam_altman_fee(...).png (89 KB, 415x707)

89 KB PNG

>>106660973
it's sentient

Anonymous
09/21/25(Sun)22:21:25 No.106661015

Anonymous 09/21/25(Sun)22:21:25 No.106661015

anime

Anonymous
09/21/25(Sun)22:45:15 No.106661132

Anonymous 09/21/25(Sun)22:45:15 No.106661132

is

Anonymous
09/21/25(Sun)22:46:58 No.106661143

Anonymous 09/21/25(Sun)22:46:58 No.106661143

gsy

Anonymous
09/21/25(Sun)22:52:51 No.106661172

Anonymous 09/21/25(Sun)22:52:51 No.106661172

I need a character card that is able to be funny. Like "intentionally" making humorous observations or comments, one that can be 4chan style of politically incorrect. What's the closest I can do?

Anonymous
09/21/25(Sun)22:55:05 No.106661185

Anonymous 09/21/25(Sun)22:55:05 No.106661185

>>106661172
LLMs are too passive for that sort of thing, they need constant pushing.
You should just write your own card anyway. It's not a big deal.

Name
Options
Comment
Verification	4chan Pass users can bypass this verification. [Learn More] [Login]
File
Please read the Rules and FAQ before posting. You may highlight syntax and preserve whitespace by using [code] tags.

Janitor applications are now being accepted. Click here to apply.