Weekly archive

New local AI models, Apr 28 – May 4, 2025

13 open models released Apr 28 – May 4, 2025, with how each runs on five reference devices.

  1. Llama Prompt Guard 2 86M

    Meta · Decision · 280M ·

    76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (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 Prompt Guard 2 22M

    Meta · Decision · 71M ·

    68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Falcon-H1 34B Instruct

    TII · LLM · 34B ·

    60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, 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

  4. MiMo 7B RL

    Xiaomi · LLM · 7.8B ·

    56Good quality (B) · 56 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

  5. Falcon-H1 7B Instruct

    TII · LLM · 7.6B ·

    50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (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-4 Mini Reasoning (3.8B)

    Microsoft · LLM · 3.8B ·

    46Fair quality (C) · 46 of 100: how capable the model is at F16, 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. Llama 3.1 Nemotron Nano 4B v1.1

    NVIDIA · LLM · 4.5B ·

    44Fair quality (C) · 44 of 100: how capable the model is at F16, 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. DeepSeek Prover V2 7B

    DeepSeek · LLM · 6.9B ·

    40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, 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

  9. Falcon-H1 3B Instruct

    TII · LLM · 3.2B ·

    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

  10. Qwen2.5-Omni 3B

    Alibaba · LLM · 5.5B ·

    30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  11. Falcon-H1 1.5B Instruct

    TII · LLM · 1.6B ·

    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

  12. Falcon-H1 0.5B Instruct

    TII · LLM · 0.5B ·

    14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  13. OLMo 2 1B Instruct

    Ai2 · LLM · 1.5B ·

    14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (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?