Weekly archive

New local AI models, May 6–12, 2024

7 open models released May 6–12, 2024, with how each runs on five reference devices.

  1. Yi 1.5 34B Chat

    01.AI · LLM · 34B ·

    47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, 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

  2. Phi-3 Medium (14B)

    Microsoft · LLM · 14B ·

    45Fair quality (C) · 45 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Phi-3 Medium 128K Instruct

    Microsoft · LLM · 14B ·

    45Fair quality (C) · 45 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. OpenChat 3.6 8B

    OpenChat · LLM · 8.0B ·

    44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, 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

  5. Phi-3 Small 8K Instruct

    Microsoft · LLM · 7.4B ·

    44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, 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

  6. Yi 1.5 9B Chat

    01.AI · LLM · 8.8B ·

    36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  7. Yi 1.5 6B Chat

    01.AI · LLM · 6.1B ·

    28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (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?