Localllm - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Kevin Tang

Sep 6

I Ran DeepSeek V4 Flash Across Two DGX Sparks Over Ethernet

#ai #hardware #localllm #networking

11 min read

Tech-Gurunomics

Sep 6

VRAM and RAM for local LLMs — honest planning bands, not a GPU tier list

#localllm #llm #ollama #hardware

4 min read

Vishnu Hari Dadhich

Sep 7

Running Ollama on a 32 GB MacBook Air: A Practical First Setup

#ai #localllm #ollama #applesilicon

6 min read

Vishnu Hari Dadhich

Sep 7

Running llama.cpp on a 32 GB MacBook Air: A Direct Comparison with Ollama

#ai #localllm #llamacpp #ollama

9 min read

Vishnu Hari Dadhich

Sep 7

Running a 35B MoE Model on an 8 GB Laptop GPU: Testing FreeToken

#ai #localllm #freetoken #gpu

7 min read

Sep 5

Temperature 0 is not reproducible. I measured 30 percent of my output changing between identical runs.

#llm #benchmarks #localllm #reproducibility

3 min read

Sep 5

Our 4B beat Claude Opus on a 440K-token corpus. Then it came last on the public benchmark.

#llm #benchmarks #localllm #privateai

4 min read

Sep 5

I told the model to separate fields with <TAB>. It did exactly that, and I lost 79 percent of my data.

#llm #prompting #debugging #localllm

3 min read

Sep 5

A 4B on a 6GB laptop matched frontier-model accuracy on aggregation — except when the answer is a number

#llm #benchmarks #localllm #agents

4 min read

Sep 5

Your agent truncates the corpus and answers anyway. Two harnesses, and a router that picks between them.

#llm #agents #localllm #benchmarks

5 min read

Aravinda 加阳

Sep 6

How to Run a Free AI Coding Assistant Locally with VS Code, opencode, and LM Studio

#tutorials #localllm #aicodingassistant #lmstudio

4 min read

Aug 18

What really fits in 8GB VRAM

#localllm #vram #gpu #buildinpublic

7 min read

Guatu

Aug 14

Moving Scheduled LLM Curation from Cloud APIs to Local Models

#aiagents #localllm #ollama #kubernetes

9 min read

Aug 11

Nine ways to talk to a local model

#localllm #ollama #llamacpp #buildinpublic

9 min read

Aug 24

A 4B model on a 6GB laptop beat Claude Opus on our 440K-token corpus. The fix was giving the model less to do.

#privateai #llm #inference #localllm

4 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.