Weekly archive

New local AI models, Jul 27 – Aug 2, 2026

6 open models released Jul 27 – Aug 2, 2026, with how each runs on five reference devices.

  1. DeepSeek V4 Flash (284B-A13B)

    DeepSeek · LLM · 304B (13.0B active) ·

    93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Inkling Small (276B-A12B)

    Thinking Machines Lab · LLM · 266B (12.0B active) ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. MiniMax H3 (33B, video + audio)

    MiniMax · Video · 20.1B ·

    90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Ling 3.0 Flash (127B-A5B)

    Ant Group (inclusionAI) · LLM · 127B (5.1B active) ·

    82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. Nemotron 3.5 Lightning 30B-A3B

    NVIDIA · LLM · 32B (3.0B active) ·

    72Great quality (A) · 72 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

  6. LFM2.5 2.6B

    Liquid AI · LLM · 2.7B ·

    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

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?