Weekly archive

New local AI models, Sep 16–22, 2024

21 open models released Sep 16–22, 2024, with how each runs on five reference devices.

  1. Qwen2.5 72B Instruct

    Alibaba · LLM · 73B ·

    69Good quality (B) · 69 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Qwen2.5 32B Instruct

    Alibaba · LLM · 33B ·

    66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Llama 3.2 90B Vision Instruct

    Meta · LLM · 89B ·

    55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, 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. Qwen2-VL 72B Instruct

    Alibaba · LLM · 73B ·

    60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. Qwen2.5 14B Instruct

    Alibaba · LLM · 15B ·

    61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  6. Illustrious XL v0.1

    OnomaAI · Image · 2.6B ·

    58Good quality (B) · 58 of 100: how capable the model is at FP8, 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

  7. Qwen2.5-Math 72B Instruct

    Alibaba · LLM · 73B ·

    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

  8. Llama Guard 3 1B

    Meta · Decision · 1.5B ·

    56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  9. CogVideoX 5B I2V

    Zhipu AI · Video · 5.6B ·

    53Fair quality (C) · 53 of 100: how capable the model is at FP8, 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

  10. Qwen2.5 Coder 7B Instruct

    Alibaba · LLM · 7.6B ·

    55Good quality (B) · 55 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  11. Mistral Small 22B (2409)

    Mistral AI · LLM · 22B ·

    51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  12. Qwen2.5 7B Instruct

    Alibaba · LLM · 7.6B ·

    52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  13. Llama 3.2 11B Vision Instruct

    Meta · LLM · 11B ·

    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

  14. Qwen2.5-Math 7B Instruct

    Alibaba · LLM · 7.6B ·

    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

  15. Llama 3.2 3B Instruct

    Meta · LLM · 3.2B ·

    35Basic quality (D) · 35 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

  16. Qwen2.5 3B Instruct

    Alibaba · LLM · 3.1B ·

    34Basic quality (D) · 34 of 100: how capable the model is at F16, 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

  17. Qwen2.5 Coder 1.5B Instruct

    Alibaba · LLM · 1.5B ·

    26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  18. Qwen2.5 1.5B Instruct

    Alibaba · LLM · 1.5B ·

    24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  19. Llama 3.2 1B Instruct

    Meta · LLM · 1.2B ·

    22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  20. Qwen2.5-Math 1.5B Instruct

    Alibaba · LLM · 1.5B ·

    20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  21. Qwen2.5 0.5B Instruct

    Alibaba · LLM · 0.5B ·

    10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (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?