Weekly archive

New local AI models, Oct 12–18, 2026

12 open models released Oct 12–18, 2026, with how each runs on five reference devices.

  1. DeepSeek V4.1 Flash 1017 (552B-A16B)

    DeepSeek · LLM · 763B (16.0B active) ·

    68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. MiniMax M3.1 Flash (428B-A23B)

    MiniMax · LLM · 429B (23.0B active) ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Ling 3.1 Flash (560B-A25B)

    Ant Group (inclusionAI) · LLM · 572B (25.0B active) ·

    90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Nemotron 3.5 Super VL 120B-A12B

    NVIDIA · LLM · 124B (12.0B active) ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, 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

  5. Fibo 2.0 Dev

    Bria AI · Image · 8.1B ·

    93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  6. Ornith 1.5 122B-A10B

    DeepReinforce · LLM · 125B (10.0B active) ·

    91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, 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

  7. FLUX 3 Image Klein

    Black Forest Labs · Image · 5.6B ·

    91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, 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

  8. Sage-A1.5 35B-A3B

    InternScience · LLM · 36B (3.0B active) ·

    91Excellent quality (A+) · 91 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

  9. Hunyuan Hy-Memory 30B-A3B

    Tencent · LLM · 30B (3.0B active) ·

    85Excellent quality (A+) · 85 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  10. LFM2.5 24B-A2B

    Liquid AI · LLM · 24B (2.5B active) ·

    74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  11. Nemotron Labs Dory 1.0 4B

    NVIDIA · LLM · 4.0B ·

    68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  12. Axion 1.0 35B

    Axion · LLM · 35B (3.0B active) ·

    62Good quality (B) · 62 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

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?