Weekly archive

New local AI models, Apr 15–21, 2024

6 open models released Apr 15–21, 2024, with how each runs on five reference devices.

  1. ProtectAI DeBERTa v3 Prompt Injection v2

    Protect AI · Decision · 180M ·

    66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

  2. Llama 3 70B Instruct

    Meta · LLM · 71B ·

    55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

  3. Mixtral 8x22B Instruct

    Mistral AI · LLM · 141B (39.0B active) ·

    52Fair quality (C) · 52 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

  4. Snowflake Arctic Instruct

    Snowflake · LLM · 479B (17.0B active) ·

    47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

  5. Llama 3 8B Instruct

    Meta · LLM · 8.0B ·

    42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

  6. Dolphin 2.9 Llama 3 8B

    Cognitive Computations · LLM · 8.0B ·

    38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?