Trending

Run LLMs on Apple Neural Engine (ANE)

Show HN: Use Third Party LLM API in JetBrains AI Assistant

Show HN: GPT-2 implemented using graphics shaders

Suno v4.5

Claude can now connect to your world

RustAssistant: Using LLMs to Fix Compilation Errors in Rust Code

LLMs for Engineering: Teaching Models to Design High Powered Rockets

Llasa: Llama-Based Speech Synthesis

XAI Dev Leaks API Key for Private SpaceX, Tesla LLMs

Qwen3-235B-A22B (no thinking) Seemingly Outperforms Claude 3.7 with 32k Thinking Tokens in Coding (Aider)

Qwen 3 30B Pruned to 16B by Leveraging Biased Router Distributions, 235B Pruned to 150B Coming Soon!

GPT-2 Implemented Using Graphics Shaders

Issue in building stuff with langGraph

Mistral-Small-3.1-24B-Instruct-2503 <32b UGI scores

Phi-3 is making small language models actually useful

SOLO Bench - A new type of LLM benchmark I developed to address the shortcomings of many existing benchmarks

Two Ais Talking in real time

LLM GPU calculator for inference and fine-tuning requirements

Qwen

Save item

Qwen3-235B-A22B

Task: text-generation

Nari Labs

Save item

Dia-1.6B

Qwen

Save item

Qwen3-30B-A3B

Task: text-generation

Qwen

Save item

Qwen3-32B

Task: text-generation

TNG Technology Consulting GmbH

Save item

DeepSeek-R1T-Chimera

Task: text-generation

Qwen

Save item

Qwen3-8B

Task: text-generation

JetBrains

Save item

Mellum-4b-base

Task: text-generation

Qwen

Save item

Qwen3-0.6B

Task: text-generation

Microsoft

Save item

Phi-4-reasoning-plus

Task: text-generation