Weekly archive

New local AI models, Apr 22–28, 2024

7 open models released Apr 22–28, 2024, with how each runs on five reference devices.

  1. DeepSeek V2 Chat

    DeepSeek · LLM · 236B (21.0B active) ·

    58Good quality (B) · 58 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

  2. Qwen1.5 110B Chat

    Alibaba · LLM · 111B ·

    43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Granite Code 34B Instruct

    IBM · LLM · 34B ·

    38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. StarCoder2 15B Instruct

    BigCode · LLM · 16B ·

    38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. Granite Code 20B Instruct

    IBM · LLM · 20B ·

    34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, 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

  6. Phi-3 Mini 128K Instruct

    Microsoft · LLM · 3.8B ·

    36Basic quality (D) · 36 of 100: how capable the model is at F16, 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. Phi-3 Mini 4K Instruct

    Microsoft · LLM · 3.8B ·

    36Basic quality (D) · 36 of 100: how capable the model is at F16, 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

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?