Llama
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
Why people recommend it
“Did you forget what sparked the whole open-weight wave? It was that.”
“I've actually seen better performance with older ones like Meta Llama 4 or Amazon's Nova”
Show 1 more
“You can run smaller models locally that are pretty good at code gen.”
Caveats and dissent
“Llama 4 was a bad model, unfortunately.”
“Meta confirmed Llama 4 benchmarks were fudged.”
Show 2 more
“I tried llama a few months back and the output was very disappointing.”
“It looked nice but the latency was not acceptable for everyday use.”
Often compared with
Who recommends it in their own words
Threads where it came up
- Facebook Pages require paid subscription to post more than two links per month 1 mention
- Your Queries Can Reorder the Retrieval Leaderboard 1 mention
- Run Qwen3.8 27B locally: real numbers from my Mac Studio 1 mention
- Why your local LLM feels dumber than it is 1 mention
- Qwen3.8 Max now ranked as the best overall model by agentic index 1 mention
- Boris Cherny on Trying to Get Claude Code to Rewrite the Claude App 1 mention
Also written as Llama 4, Llama 3, Llama 3.3 70B, Llama 3.1. Data: llama.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 16
“Did you forget what sparked the whole open-weight wave? It was that.”
“gemini-2.5-pro, claude-opus-4.8, gpt-5.1, llama-3.3-70b”
“llama 3.1 8b q8_0 does about 70tk/s”
“I have been using open source LLMs locally for the past 5 months like Qwen, Llama, DeepSeek and others”
“Some small 8b models (like llama3.1) for sentiment analysis on text.”
“I've actually seen better performance with older ones like Meta Llama 4 or Amazon's Nova”
“Llama 4 was a bad model, unfortunately.”
“a LangGraph + Groq Llama 3.3 70B agent that reads GitHub PRs and issues”
“Meta confirmed Llama 4 benchmarks were fudged.”
“You can run smaller models locally that are pretty good at code gen.”
“We tested with Qwen and LLaMA base models.”
“I use Llama 3 to translate natural language rules into "JSON Logic"”
“With Groq speed (Llama 3 @ 800t/s)”
“I tried llama a few months back and the output was very disappointing.”
“It looked nice but the latency was not acceptable for everyday use.”
“I use ollama in openwebui and llama3 in model.”