Skip to content
Local AI Wizard
Your machine
Theme

What are the best local AI models for 32 GB?

The reviewed models that run well on 32 GB, ranked by each quality source.

Memory · updated

Short answer

35models

35 reviewed text models run well on 32 GB, on a graphics card or a Mac. The strongest by each source:

  • LMArena: Gemma 4 31B, Gemma 4 26B A4B, and Qwen3.8 27B
  • LiveBench: Smaug Mini, Qwen3.8 27B, and Qwen3.6 27B
  • Two separate rankings: the site never mixes them.

Computed from the reviewed catalog with the site's fit rule; scores from LiveBench and LMArena. Methodology

How this list is made

This page is computed from the site's catalog every time it is built, so it moves with the data instead of going stale. It takes every reviewed open text model with a published parameter count and asks the same question the hardware pages ask: does its Q4 file, plus working room and the machine's reserve, fit in fast memory? A model is listed here when it runs well on both reference machines: RTX 5090 · 32 GB VRAM, which keeps 2 GB of the card aside, and Mac mini M4 · 32 GB unified, which keeps 25% of its memory (8 GB) for macOS and your apps.

Quality comes from two sources that are never mixed: LiveBench (2026-06-25), test questions scored 0 to 100, and LMArena (2026-10-22), a rating from blind human votes. Each has its own table below. 18 of the 35 models have neither score yet; they still run well and are in the full table below. How to read the scores.

Top by LMArena

Blind human preference, 2026-10-22 release. Q4 need includes each machine's reserve.

Top reviewed models by LMArena 2026-10-22 that run well on 32 GB.
Model · publisher · parametersLMArena 2026-10-22 (rating)Q4 need, card / Mac (GB)
Gemma 4 31B
Google · 30.7B
1,45226 / 32
Gemma 4 26B A4B
Google · 25.2B
1,43721 / 27
Qwen3.8 27B
Alibaba · 27B
1,43723 / 29
Qwen3 30B A3B Instruct 2507
Alibaba · 30.5B
1,38225 / 31
GLM-4.7 Flash
Z.ai · 30B
1,36525 / 31

Top by LiveBench

Test questions, 2026-06-25 release, 0–100. Q4 need includes each machine's reserve.

Top reviewed models by LiveBench 2026-06-25 that run well on 32 GB.
Model · publisher · parametersLiveBench 2026-06-25 (0–100)Q4 need, card / Mac (GB)
Smaug Mini
Abacus AI · 27B
76.923 / 29
Qwen3.8 27B
Alibaba · 27B
75.323 / 29
Qwen3.6 27B
Alibaba · 27B
6423 / 29

Every model that runs well

35 reviewed text models, scored or not. Ordered by Hub downloads over 30 days, read 2026-10-25, not by quality; sort a score column to rank by that source alone.

Every reviewed text model that runs well on 32 GB
Qwen3 14BAlibaba · 14.8BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-2214 / 209.0Apache 2.010.4M
Gemma 4 31BGoogle · 30.7BNot in LiveBench 2026-06-251,45226 / 3218.3Apache 2.08.4M
Gemma 4 26B A4BGoogle · 25.2BNot in LiveBench 2026-06-251,43721 / 2716.9Apache 2.08.2M
Qwen3 8BAlibaba · 8.2BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-229 / 155.0Apache 2.08.1M
Qwen3.8 27BAlibaba · 27B75.31,43723 / 2916.5Apache 2.07.8M
Qwen3.5 9BAlibaba · 9BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-229 / 155.7Apache 2.06.1M
gpt-oss-20bOpenAI · 21BNot in LiveBench 2026-06-251,31718 / 2411.6Apache 2.05.8M
Llama 3.1 8B InstructMeta · 8BNot in LiveBench 2026-06-251,2118 / 144.9Llama 3.14.8M
8 of 35

The full lists

Each hardware page lists every model, scored or not, with files and sources.

RTX 5090 · 32 GB VRAM
37 reviewed text models run well0 more run slowly with part of the model in PC RAM (32 GB assumed).
Mac mini M4 · 32 GB unified
35 reviewed text models run wellThe Mac shares this memory with macOS and keeps 8 GB aside (the card keeps 2 GB), so its planning need is higher for the same file.