Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
localai
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
How I Run a 27B Local Agent on a 12GB Laptop GPU: KVMem, Tiered KV, and Honest Long-Context Limits
Sparkle Qwen27b
Sparkle Qwen27b
Sparkle Qwen27b
Follow
Nov 19
How I Run a 27B Local Agent on a 12GB Laptop GPU: KVMem, Tiered KV, and Honest Long-Context Limits
#
llm
#
localai
#
gpu
#
opensource
Comments
Add Comment
6 min read
Moderation
NVFP4 Won't Save Your VRAM: Quantization Tradeoffs on a 12GB Laptop GPU
Sparkle Qwen27b
Sparkle Qwen27b
Sparkle Qwen27b
Follow
Nov 19
NVFP4 Won't Save Your VRAM: Quantization Tradeoffs on a 12GB Laptop GPU
#
llm
#
localai
#
gpu
#
opensource
Comments
Add Comment
3 min read
Moderation
[Phân tích kỹ thuật] NVIDIA Mở Bán RTX Spark: Máy Tính Để Bàn Nhỏ Gọn 1 Petaflop, Đưa AI Agent Và Blackwell Về Bàn Làm Việc
Tin Tức AI
Tin Tức AI
Tin Tức AI
Follow
Nov 19
[Phân tích kỹ thuật] NVIDIA Mở Bán RTX Spark: Máy Tính Để Bàn Nhỏ Gọn 1 Petaflop, Đưa AI Agent Và Blackwell Về Bàn Làm Việc
#
nvidiartxspark
#
nvidiablackwell
#
cpugrace
#
localai
Comments
Add Comment
10 min read
Moderation
Скачал полтерабайта локальных LLM — но без GPU жизни нет
Alexey Bolshakov
Alexey Bolshakov
Alexey Bolshakov
Follow
Nov 19
Скачал полтерабайта локальных LLM — но без GPU жизни нет
#
ai
#
localai
#
gpu
#
agents
Comments
Add Comment
12 min read
Moderation
Unsloth Dynamic V3.1: Qwen3.8-27B Local Agent Benchmarks
[email protected]
[email protected]
[email protected]
Follow
Nov 17
Unsloth Dynamic V3.1: Qwen3.8-27B Local Agent Benchmarks
#
quantization
#
llmserving
#
localai
#
qwen
Comments
Add Comment
1 min read
Moderation
Local AI on a PC: what actually works (Whisper, translation, LLMs)
CJDARKLORD
CJDARKLORD
CJDARKLORD
Follow
Nov 19
Local AI on a PC: what actually works (Whisper, translation, LLMs)
#
ai
#
machinelearning
#
localai
#
gpu
1
reaction
Comments
Add Comment
2 min read
Moderation
Faire tourner un MoE de 35B sur une GTX 1650 4 Go : le test réel
Nabil Doghri
Nabil Doghri
Nabil Doghri
Follow
Nov 17
Faire tourner un MoE de 35B sur une GTX 1650 4 Go : le test réel
#
ai
#
llm
#
ollama
#
localai
Comments
Add Comment
7 min read
Moderation
Hybrid AI setups seem to be most practical setup right now compared to fully local (for certain workflows)
Aaron Vaz
Aaron Vaz
Aaron Vaz
Follow
Nov 17
Hybrid AI setups seem to be most practical setup right now compared to fully local (for certain workflows)
#
ai
#
webdev
#
localai
#
llm
2
reactions
Comments
2
comments
2 min read
Moderation
Local AI Development with the Surface Laptop Ultra
Holger Imbery
Holger Imbery
Holger Imbery
Follow
Nov 18
Local AI Development with the Surface Laptop Ultra
#
arm64
#
foundrylocal
#
githubcopilot
#
localai
Comments
Add Comment
42 min read
Moderation
datasette-llm 0.1a11:通过 OpenAI 兼容接口接入本地模型
arthur
arthur
arthur
Follow
Nov 15
datasette-llm 0.1a11:通过 OpenAI 兼容接口接入本地模型
#
datasette
#
llm
#
localai
#
sql
Comments
1
comment
1 min read
Moderation
Klepai v0.1.0: regenerate keeps your old answer
Crystal Studio
Crystal Studio
Crystal Studio
Follow
Nov 15
Klepai v0.1.0: regenerate keeps your old answer
#
ollama
#
opensource
#
localai
#
agents
Comments
Add Comment
3 min read
Moderation
llama.cpp 1.0.0 Stabilizes the Local Inference API — Dual-Track WASAPI Capture Still Owns the Latency Budget
devs
devs
devs
Follow
Nov 14
llama.cpp 1.0.0 Stabilizes the Local Inference API — Dual-Track WASAPI Capture Still Owns the Latency Budget
#
llamacpp
#
windows
#
audio
#
localai
Comments
Add Comment
4 min read
Moderation
Running Mano-P on the Cheapest Mac It Survives On
Mininglamp
Mininglamp
Mininglamp
Follow
Nov 12
Running Mano-P on the Cheapest Mac It Survives On
#
ai
#
opensource
#
apple
#
localai
1
reaction
Comments
Add Comment
3 min read
Moderation
Speech Studio 0.5.0 Drops Local Multi-Engine TTS+STT on Windows — First-Sound Latency Still Sets the Overlay Floor
devs
devs
devs
Follow
Nov 11
Speech Studio 0.5.0 Drops Local Multi-Engine TTS+STT on Windows — First-Sound Latency Still Sets the Overlay Floor
#
windows
#
audio
#
stt
#
localai
Comments
Add Comment
4 min read
Moderation
How to make a local AI model give the same answer every time
Hanako H.
Hanako H.
Hanako H.
Follow
Nov 9
How to make a local AI model give the same answer every time
#
ai
#
llm
#
localai
#
tutorial
Comments
Add Comment
3 min read
Moderation
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account