Weekly archive

New local AI models, Mar 11–17, 2024

12 open models released Mar 11–17, 2024, with how each runs on five reference devices.

  1. BGE Reranker v2 Gemma

    BAAI · Decision · 2.5B ·

    78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. BGE Reranker v2 M3

    BAAI · Decision · 570M ·

    72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Animagine XL 3.1

    Cagliostro Lab · Image · 2.6B ·

    54Fair quality (C) · 54 of 100: how capable the model is at FP8, 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

  4. Command R 35B (v01)

    Cohere · LLM · 35B ·

    51Fair quality (C) · 51 of 100: how capable the model is at Q4_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

  5. Grok-1 (314B)

    xAI · LLM · 314B (86.0B active) ·

    42Fair quality (C) · 42 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

  6. Code Llama 70B Instruct

    Meta · LLM · 69B ·

    41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  7. LLaVA 1.6 34B

    LLaVA · LLM · 35B ·

    41Fair quality (C) · 41 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

  8. Code Llama 34B Instruct

    Meta · LLM · 34B ·

    36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  9. Hermes 2 Pro Mistral 7B

    Nous Research · LLM · 7.2B ·

    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

  10. Code Llama 13B Instruct

    Meta · LLM · 13B ·

    29Basic quality (D) · 29 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  11. Code Llama 7B Instruct

    Meta · LLM · 6.7B ·

    24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, 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

  12. Qwen1.5 MoE A2.7B Chat

    Alibaba · LLM · 14B (2.7B active) ·

    24Basic quality (D) · 24 of 100: how capable the model is at F16, 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?