|
Qwen3.5-27B at 4-bit, fully on a single RTX 5080: ~50 tok/s at 32k context, plus a complete local agent around it
|
|
1
|
31
|
October 18, 2026
|
|
Generation is cheap, gating is the work: 48 hours building an anti-slop review lane for open-source app submissions
|
|
7
|
152
|
October 18, 2026
|
|
Shoe string ablation or pruning
|
|
16
|
343
|
October 17, 2026
|
|
[Looking for Testers] Got an old NVIDIA GPU with at least 2GB VRAM? Help us build a decentralized AI network!
|
|
9
|
161
|
October 18, 2026
|
|
How would you evaluate a personal AI for invented memories and revoked consent?
|
|
8
|
125
|
October 18, 2026
|
|
Running small LLMs locally — what hardware are you using in 2026?
|
|
4
|
276
|
October 17, 2026
|
|
Getting two-column reading order, ruled tables and CJK text right when converting PDFs to Markdown for RAG
|
|
4
|
63
|
October 18, 2026
|
|
AlterEgo: Towards the Zero-Cost Personal Agent - open-source Windows-native agent at $0 model cost
|
|
4
|
73
|
October 18, 2026
|
|
Separate forenames and surnames in DOI generation
|
|
2
|
94
|
October 18, 2026
|
|
Optimization query: Training efficiency on Abliterated vs. Raw checkpoints
|
|
1
|
58
|
October 17, 2026
|
|
Account locked after old Space was flagged — appeal pending (#47084 / #47517 / #47520)
|
|
1
|
58
|
October 17, 2026
|
|
Arabic (Egyptian dialect) veterinary diagnosis assistant: dialect -> clinical-English gap and low accuracy on real owner messages
|
|
3
|
78
|
October 16, 2026
|
|
Flinch test: can self-referential retreats be measured reproducibly? Seeking independent tests
|
|
4
|
74
|
October 18, 2026
|
|
I built a small language model from scratch. Here's how it works
|
|
0
|
34
|
October 17, 2026
|
|
How to keep what the model makes up out of the agent
|
|
14
|
214
|
October 18, 2026
|
|
What Should I Learn First?
|
|
3
|
131
|
October 18, 2026
|
|
AI, Mathematics, and the Possibility of an “Information Field”
|
|
8
|
225
|
October 17, 2026
|
|
Anyone else having trouble getting a ZeroGPU allocation/reservation?
|
|
37
|
1925
|
October 13, 2026
|
|
Crux: an open-source toolbox for agentic computational research
|
|
3
|
68
|
October 18, 2026
|
|
AI Safety is Not Ethics, It’s Plumbing: A Thermodynamic Framework for Agentic AI Loops
|
|
0
|
33
|
October 16, 2026
|
|
What does a AI judge score of 0.8 actually mean? Introducing Typed Evals
|
|
5
|
177
|
October 18, 2026
|
|
Smallwords: controlled-vocabulary generation with one inspectable contract
|
|
2
|
57
|
October 17, 2026
|
|
We gave AI a trust we never gave people - The third axis, after capability and permission
|
|
10
|
534
|
October 8, 2026
|
|
Wan2gp best setting for fasteste generation
|
|
3
|
137
|
October 16, 2026
|
|
Two models on one 8 GB GPU: making the LLM wait for the TTS after every sentence stopped my voice assistant from stuttering
|
|
3
|
108
|
October 17, 2026
|
|
Finding overflow and NaN edge cases in numerical code: numguard
|
|
1
|
46
|
October 16, 2026
|
|
Pls Add NVIDIA Tesla P4 8GB
|
|
1
|
71
|
October 15, 2026
|
|
Best model to help to keep system in line
|
|
2
|
110
|
October 17, 2026
|
|
Could RAG retrieve LLM-native latent memory instead of text?
|
|
7
|
187
|
October 14, 2026
|
|
innoai/Edge-TTS-Text-to-Speech
|
|
2
|
77
|
October 17, 2026
|