Hackernews posts about Mixtral

1. Tell HN: We've come a long way since GPT-3 days
   3 points by behnamoh 23 days ago | discuss
2. Mistral ships Le Chat – enterprise AI assistant that can run on prem (mistral.ai)
   508 points by _lateralus_ 17 days ago | 158 comments
3. Mistral's new Devstral AI model was designed for coding (techcrunch.com)
   8 points by Sourabhsss1 3 days ago | discuss
4. Mistral Document AI (mistral.ai)
   4 points by ianhawes 1 day ago | discuss
5. Mistral launches chatbot for companies, triples revenue in 100 days (www.reuters.com)
   3 points by saubeidl 16 days ago | discuss
6. Thoughts on Mistral.rs (github.com)
   2 points by ericlbuehler 24 days ago | 2 comments
7. Show HN: MistralOCR with Web Search ADK Agent App (github.com)
   2 points by tested1 5 days ago | discuss
8. Show HN: Lailaims – Talk to multiple LLMs at once (lailaims.pages.dev)
   6 points by youz 7 days ago | discuss
9. Show HN: LocoStudio - A better UI for Ollama (www.locostudio.ai)
   6 points by simmy345 17 days ago | discuss
10. Show HN: Ragmate – Local RAG server for JetBrains with project-aware context (github.com)
    4 points by scream4ik 12 days ago | discuss
11. Show HN: Ridvay Code – An AI Coding Assistant for VS Code (ridvay.com)
    3 points by Tom-G 19 days ago | 2 comments
12. Show HN: Conductor Tasks MCP: Task Manager for AI Development (github.com)
    1 points by hridyaagrawal 10 days ago | discuss
13. Show HN: LogWhisperer – Local AI-powered system log summarizer (no API keys)
    1 points by binary-knight 18 days ago | discuss
14. Devstral (mistral.ai)
    681 points by mfiguiere 3 days ago | 141 comments
15. Medium Is the New Large (mistral.ai)
    70 points by Philpax 17 days ago | 20 comments
16. Show HN: DemoDazzle – Create Interactive Demos Without Code (demodazzle.sutracms.com)
    1 points by qareena 11 days ago | discuss
17. Groq runs Mixtral 8x7B-32k with 500 T/s (groq.com)
    847 points by tin7in over 1 year ago | 472 comments
18. Mixtral of experts (mistral.ai)
    639 points by georgehill over 1 year ago | 300 comments
19. Mistral "Mixtral" 8x7B 32k model [magnet] (twitter.com)
    546 points by xyzzyrz over 1 year ago | 239 comments
20. Mixtral 8x22B (mistral.ai)
    533 points by meetpateltech about 1 year ago | 242 comments
21. Mixtral 8x7B: A sparse Mixture of Experts language model (arxiv.org)
    359 points by ignoramous over 1 year ago | 150 comments
22. My AI costs went from $100 to less than $1/day: Fine-tuning Mixtral with GPT4 (twitter.com)
    278 points by ignoramous over 1 year ago | 122 comments
23. Brave Leo now uses Mixtral 8x7B as default (brave.com)
    244 points by b_mc2 over 1 year ago | 178 comments
24. Mistral AI launches Mixtral-Next (chat.lmsys.org)
    204 points by varunvummadi over 1 year ago | 49 comments
25. Ollama 0.1.32: WizardLM 2, Mixtral 8x22B, macOS CPU/GPU model split (github.com)
    107 points by tosh about 1 year ago | 55 comments
26. Visualizing expert firing frequencies in Mixtral MoE (mixtral-moe-vis-d726c4a10ef5.herokuapp.com)
    99 points by tosh over 1 year ago | 23 comments
27. Mistral's mixtral-8x7B-32kseqlen on Vercel (twitter.com)
    67 points by tosh over 1 year ago | 30 comments
28. Mixtral 8x22B Model (twitter.com)
    54 points by shenli3514 about 1 year ago | 2 comments
29. Show HN: Code interpreter with mixtral-8x7B-instruct (github.com)
    35 points by sonlight03 over 1 year ago | discuss
30. Mixtral-8x22B on HuggingFace (huggingface.co)
    33 points by milliondreams about 1 year ago | 3 comments
31. Zephyr 141B, a Mixtral 8x22B fine-tune, is now available in Hugging Chat (huggingface.co)
    30 points by osanseviero about 1 year ago | 12 comments
32. Mixtral 8x7B going 378 tokens per second on CPU (twitter.com)
    28 points by tosh about 1 year ago | 6 comments
33. Mixtral 8x22B on MLX (twitter.com)
    20 points by tosh about 1 year ago | 3 comments
34. Show HN: The fastest way to run Mixtral 8x7B on Apple Silicon Macs
    18 points by woadwarrior01 about 1 year ago | 22 comments
35. Mixtral-8x22B-Instruct-v0.1 (huggingface.co)
    18 points by tosh about 1 year ago | 2 comments
36. Show HN: Like grep but for natural questions. Mixtral 8x7B – 28 tok/s on 8GB GPU (github.com)
    10 points by molli about 1 year ago | discuss
37. Mixtral 8x22B latest-model benchmarks (www.promptzone.com)
    9 points by adif_sgaid about 1 year ago | 4 comments
38. Argilla released Notux 8x7B - DPO fine-tune of Mixtral 8x7B (huggingface.co)
    9 points by alvarobartt over 1 year ago | 1 comments
39. Show HN: I made a VS Code extension where you can use Mixtral 8x7B for free (marketplace.visualstudio.com)
    8 points by fmdz over 1 year ago | discuss
40. Llamafile 0.4 now with Mixtral support (github.com)
    6 points by louismerlin over 1 year ago | 1 comments
41. Show HN: Chat with Mixtrals – AI Characters That Make Art (netwrck.com)
    5 points by leeeeeep101 over 1 year ago | 6 comments
42. New Mixtral HQQ Quantzied 4-bit/2-bit configuration (huggingface.co)
    5 points by ibuildthings over 1 year ago | 1 comments
43. The latest major open LLM releases: Mixtral, Llama 3, Phi-3, and OpenELM (magazine.sebastianraschka.com)
    5 points by rasbt about 1 year ago | discuss
44. Mixtral AI generated comment to US regulators about Open Models (www.regulations.gov)
    5 points by Der_Einzige about 1 year ago | discuss
45. Cosmopedia: the largest synthetic dataset of textbooks generated by Mixtral (huggingface.co)
    5 points by loubnabnl over 1 year ago | discuss
46. Mixtral on MLX (github.com)
    5 points by tosh over 1 year ago | discuss