Inference

[-]
Forum Threads Posts Last Post
Forum Announcements
 8 79 Welcome to the new Data S...
10-12-2026, 02:24 AM
by Data Sculpting
Community Announcements
 4 31 Announcing VisLlama - a U...
10-19-2026, 05:25 AM
by Data Sculpting

[-]
Forum Threads Posts Last Post
GPUs
 47 441 RTX 5090 local inference ...
10-19-2026, 05:54 AM
by circuitwire58
Systems & Builds
 32 310 power delivery for 24/7 s...
10-19-2026, 03:51 AM
by bytegarden73
CPUs / NPUs / Accelerators
 19 155 do small edge boxes make ...
10-19-2026, 03:27 AM
by routeline23

[-]
Forum Threads Posts Last Post
NVIDIA / CUDA
 48 411 CUDA update broke my thro...
10-19-2026, 05:57 AM
by dockember
AMD / ROCm
 38 277 ROCm version that finally...
10-19-2026, 01:16 AM
by cozykite
Apple / MLX
 32 266 MLX model loading quirks
10-19-2026, 05:21 AM
by visionyard23
PyTorch / JAX / Other Frameworks
 31 311 PyTorch compile got faste...
10-19-2026, 03:31 AM
by deepseeked

[-]
Forum Threads Posts Last Post
llama.cpp / GGUF
 48 465 context size vs speed in ...
10-19-2026, 05:58 AM
by macroforge
vLLM / SGLang
 48 372 prefill/decode separation...
10-19-2026, 05:38 AM
by oxidemixer
TensorRT-LLM
 32 282 when TensorRT-LLM clearly...
10-19-2026, 02:46 AM
by batchcraft
Ollama / LM Studio / Desktop Runtimes
 32 251 desktop runtimes for non-...
10-19-2026, 03:35 AM
by localcraft17
Other Engines
 54 465 throughput per watt reali...
10-19-2026, 05:28 AM
by kernelhouse70

[-]
Forum Threads Posts Last Post
Quantization
 32 279 quant choices for 70B loc...
10-19-2026, 05:26 AM
by relaynest82
Context / KV Cache
 38 346 paged attention observati...
10-19-2026, 04:23 AM
by audioriver
Performance Tuning
 32 317 what changed after the in...
10-19-2026, 04:31 AM
by macropilot
Benchmarks
 25 245 first LoRA that actually ...
10-19-2026, 03:40 AM
by localtinker

[-]
Forum Threads Posts Last Post
Agents
 19 169 distillation that keeps u...
10-18-2026, 05:12 PM
by mangowire
Routers
 19 161 dataset format recommenda...
10-19-2026, 02:53 AM
by routecraft
MCP / APIs / Tool Calling
 13 69 frankenmerges anyone kept...
10-18-2026, 09:57 PM
by sparrowcraft
Workflows / Automation
 25 217 DeepSeek V4.1 impressions...
10-19-2026, 02:55 AM
by quantshed

[-]
Forum Threads Posts Last Post
Proprietary / Frontier
 42 373 where open models feel su...
10-19-2026, 05:25 AM
by deltagrid
Open Weight

Sub Forums:
Hosted,
Local, and 1 more.
92 788 simple router policy idea...
10-19-2026, 05:27 AM
by macronest
Embedding / Reranking Models
 19 157 clean API wrappers for lo...
10-18-2026, 11:41 PM
by signalcraft14

[-]
Forum Threads Posts Last Post
Fine-Tuning / LoRA
 19 141 workflow automation with ...
10-19-2026, 03:34 AM
by thetanest
Distillation
 25 198 when RAG was overkill
10-19-2026, 12:02 AM
by mangohouse
Dataset Creation / Curation
 19 142 embedding model you trust...
10-19-2026, 05:44 AM
by latentscope35
Model Merging
 19 183 do you even need a vector...
10-19-2026, 01:56 AM
by dockember

[-]
Forum Threads Posts Last Post
RAG
 32 283 where reranking mattered
10-19-2026, 05:46 AM
by batchshed
Embeddings
 25 203 Help with Embeddings for ...
10-19-2026, 01:38 AM
by ggufwire22
Vector Databases
 19 168 Help with Vector Database...
10-19-2026, 04:43 AM
by emberquill
Search / Retrieval / Reranking
 25 172 Search / Retrieval / Rera...
10-19-2026, 01:43 AM
by macrolab

[-]
Forum Threads Posts Last Post
Prompts / System Prompts
 25 249 few-shot when you actuall...
10-19-2026, 05:49 AM
by vramstream
Structured Output
 19 171 structured output failure...
10-19-2026, 03:11 AM
by audiodesk
Long Context / Memory
 19 152 long context that stayed ...
10-19-2026, 03:05 AM
by latentscope35

[-]
Forum Threads Posts Last Post
Benchmarks
 25 224 benchmark result I don't ...
10-19-2026, 05:03 AM
by routearch
Evals
 25 226 human evals on small team...
10-19-2026, 01:43 AM
by audioriver
Model Comparisons
 19 177 flux pipeline local tips ...
10-19-2026, 04:47 AM
by kernelmike
Quality / Reliability Testing
 19 192 local video generation re...
10-18-2026, 10:27 PM
by kernelghost

[-]
Forum Threads Posts Last Post
Image
 25 246 whisper alternatives late...
10-19-2026, 04:33 AM
by audiorunner74
Video
 19 150 multimodal local stack th...
10-19-2026, 04:14 AM
by forgemixer
Audio / Speech
 19 149 Help with Audio / Speech:...
10-19-2026, 02:49 AM
by sparrowhall
Multimodal
 13 99 Multimodal discussion
10-18-2026, 05:50 PM
by cudaworks

[-]
Forum Threads Posts Last Post
Online / Hosted
 19 198 tools worth paying for
10-19-2026, 05:52 AM
by macronest
Local
 38 352 CLI helpers for local mod...
10-19-2026, 05:42 AM
by mintstation99

[-]
Forum Threads Posts Last Post
Mobile
 19 169 running local models on a...
10-19-2026, 04:39 AM
by sparrowworks88
SBCs / Mini PCs
 18 187 SBC inference experiments
10-19-2026, 04:12 AM
by lablab
AI Devices
 13 97 dedicated AI gadgets you ...
10-19-2026, 03:03 AM
by routecrate

[-]
Forum Threads Posts Last Post
Local Privacy
 13 113 what truly stays local wi...
10-19-2026, 01:25 AM
by cobaltspark
Model / Agent Security
 13 118 sandboxing agent actions
10-19-2026, 02:10 AM
by turboscope5
Sandboxing
 13 111 containment for model-dri...
10-19-2026, 02:34 AM
by tinycontext

[-]
Forum Threads Posts Last Post
General
 42 380 what are you all running ...
10-19-2026, 04:56 AM
by plaingarden18
News & Industry
 49 416 driver/framework news rou...
10-19-2026, 05:35 AM
by southpatch
Off Topic
 28 210 FC 27 Season 2 Coins Guid...
8 hours ago
by salisy

[-]
Board Statistics
Who's Online [Complete List]
211 users active in the past 15 minutes (0 members, 0 of whom are invisible, and 209 guests).
Bing, Google
Board Statistics
Our members have made a total of 4 posts in 4 threads.
We currently have 5 members registered.
Please welcome our newest member, DataSculptingIT
The most users online at one time was 1,089 on Today at 05:04 AM
Forum Statistics

Forum Contains New Posts
Forum Contains No New Posts
Forum is Closed
Redirect Forum