Weekly archive

New local AI models, Apr 7–13, 2025

14 open models released Apr 7–13, 2025, with how each runs on five reference devices.

  1. Llama 3.1 Nemotron Ultra 253B v1

    NVIDIA · LLM · 253B ·

    81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. GLM-4 32B 0414

    Zhipu AI · LLM · 33B ·

    70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. GLM-Z1 32B (0414)

    Zhipu AI · LLM · 33B ·

    70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. InternVL3 78B

    Shanghai AI Lab · LLM · 78B ·

    70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, 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

  5. InternVL3 38B

    Shanghai AI Lab · LLM · 38B ·

    66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, 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. Phi-4 Reasoning (14B)

    Microsoft · LLM · 15B ·

    69Good quality (B) · 69 of 100: how capable the model is at Q6_K, 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

  7. DeepCoder 14B Preview

    Agentica · LLM · 15B ·

    63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  8. InternVL3 14B

    Shanghai AI Lab · LLM · 15B ·

    63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  9. GLM-Z1 9B (0414)

    Zhipu AI · LLM · 9.4B ·

    58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  10. InternVL3 8B

    Shanghai AI Lab · LLM · 7.9B ·

    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

  11. GLM-4 9B 0414

    Zhipu AI · LLM · 9.4B ·

    52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  12. Kimi-VL A3B Instruct

    Moonshot AI · LLM · 16B (3.0B active) ·

    50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  13. Granite 3.3 8B

    IBM · LLM · 8.2B ·

    46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, 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

  14. Granite 3.3 2B

    IBM · LLM · 2.5B ·

    30Basic quality (D) · 30 of 100: how capable the model is at F16, 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

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?