Weekly archive

New local AI models, Oct 5–11, 2026

11 open models released Oct 5–11, 2026, with how each runs on five reference devices.

  1. Beam 1.0 (501B-A23B)

    Reflection AI · LLM · 501B (23.4B active) ·

    89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. MiniCPM-V 4.7 35B-A3B

    OpenBMB · LLM · 35B (3.0B active) ·

    93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Nemotron 3.5 Bolt 74B-A9B

    NVIDIA · LLM · 75B (9.0B active) ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Qwen-Image 2.1 Turbo

    Alibaba · Image · 7.1B ·

    89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. MOSS-Image SFT

    OpenMOSS · Image · 5.1B ·

    82Great quality (A) · 82 of 100: how capable the model is at FP16, 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

  6. d1 3B

    Liquid AI · Decision · 3.1B ·

    82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  7. LemonDecider 4B

    Ant Group (inclusionAI) · Decision · 4.5B ·

    80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  8. Iris-3B

    Speridlabs · Image · 3.0B ·

    72Great quality (A) · 72 of 100: how capable the model is at FP16, 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

  9. Nemotron 3.5 Bolt E4B

    NVIDIA · LLM · 8.0B ·

    70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  10. LightOnOCR-3 4B

    LightOn · LLM · 4.5B ·

    48Fair quality (C) · 48 of 100: how capable the model is at F16, 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

  11. MiniCPM-V 4.7 1B

    OpenBMB · LLM · 1.6B ·

    40Fair quality (C) · 40 of 100: how capable the model is at F16, 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

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?