The best local LLMs right now
We tested 56 AI models you can run on your own computer. Here's the best one for every graphics card and Mac.
Rankings
Best local LLM for coding: we ran the code
56 models, 30 programming jobs, each checked against tests the model never saw. Here's who writes code that works.
Rankings
Decision models vs. regular LLMs: 14 free models beat the best one
68 models, 56 real decisions: routing tickets, spotting phishing, flagging risky code. Accuracy and how honest their confidence is.
Rankings
We made our document test harder. Here's what changed
Most models used to ace it. Now only a handful do, and the rankings moved a lot.
News
We tested Mistral Large 4 ("Le Chonk"). It's brilliant when it stops thinking
Every program it finished was correct, and it beat every local model at reading documents. But on 12 of 30 coding jobs it never gave an answer at all.
News
gpt-oss-120b review: one of the best local models we've tested
It scored 96 out of 100, #2 of 56. It solved 28 of 30 coding jobs and scored 99 on reading documents. Runs on a Mac with 96 GB.
Reviews
Muse Glimmer 30B review: one of the best local models we've tested
It scored 94 out of 100, #3 of 56. It solved 27 of 30 coding jobs and scored 98 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Ling 3.0 Flash review: a solid all-rounder
It scored 94 out of 100, #4 of 56. It solved 28 of 30 coding jobs and scored 95 on reading documents. Runs on a Mac with 128 GB.
Reviews
GLM 4.5V review: a solid all-rounder
It scored 93 out of 100, #5 of 56. It solved 26 of 30 coding jobs and scored 99 on reading documents. Runs on a Mac with 96 GB.
Reviews
Ling 3.0 Flash VL review: a solid all-rounder
It scored 92 out of 100, #6 of 56. It solved 26 of 30 coding jobs and scored 98 on reading documents. Runs on a Mac with 128 GB.
Reviews
Laguna XS 2.1 review: a solid all-rounder
It scored 82 out of 100, #12 of 56. It solved 22 of 30 coding jobs and scored 91 on reading documents. Runs on a 24 GB graphics card or a Mac with 48 GB.
Reviews
GLM 4.5 Air review: decent, with trade-offs
It scored 76 out of 100, #18 of 56. It solved 21 of 30 coding jobs and scored 82 on reading documents. Runs on a Mac with 96 GB.
Reviews
GLM 4.6V review: decent, with trade-offs
It scored 73 out of 100, #19 of 56. It solved 22 of 30 coding jobs and scored 73 on reading documents. Runs on a Mac with 96 GB.
Reviews
Laguna S 2.1 review: decent, with trade-offs
It scored 64 out of 100, #25 of 56. It solved 21 of 30 coding jobs and scored 59 on reading documents. Runs on a Mac with 128 GB.
Reviews
Nex-N2.5-Mini review: not one we'd recommend right now
It scored 57 out of 100, #27 of 56. It solved 8 of 30 coding jobs and scored 88 on reading documents. Runs on a 24 GB graphics card or a Mac with 48 GB.
Reviews
Devstral 2 2512 review: not one we'd recommend right now
It scored 53 out of 100, #28 of 56. It solved 16 of 30 coding jobs and scored 53 on reading documents. Runs on a Mac with 128 GB.
Reviews
Hunyuan A13B Instruct review: not one we'd recommend right now
It scored 52 out of 100, #29 of 56. It solved 11 of 30 coding jobs and scored 67 on reading documents. Runs on a Mac with 96 GB.
Reviews
Qwen2.5 72B Instruct review: not one we'd recommend right now
It scored 46 out of 100, #31 of 56. It solved 12 of 30 coding jobs and scored 52 on reading documents. Runs on a Mac with 64 GB.
Reviews
Llama 3.3 70B Instruct review: not one we'd recommend right now
It scored 46 out of 100, #33 of 56. It solved 14 of 30 coding jobs and scored 45 on reading documents. Runs on a Mac with 64 GB.
Reviews
Command A review: not one we'd recommend right now
It scored 45 out of 100, #34 of 56. It solved 10 of 30 coding jobs and scored 56 on reading documents. Runs on a Mac with 96 GB.
Reviews
Llama 3.1 70B Instruct review: not one we'd recommend right now
It scored 39 out of 100, #41 of 56. It solved 10 of 30 coding jobs and scored 44 on reading documents. Runs on a Mac with 64 GB.
Reviews
Llama 3.3 8B Instruct (Q4, Mac) review: not one we'd recommend right now
It scored 23 out of 100, #47 of 56. It solved 4 of 30 coding jobs and scored 33 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Granite 4.0 Micro (Q4, Mac) review: not one we'd recommend right now
It scored 22 out of 100, #49 of 56. It solved 4 of 30 coding jobs and scored 31 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Qwen2.5 VL 72B Instruct review: not one we'd recommend right now
It scored 14 out of 100, #53 of 56. It solved 4 of 30 coding jobs and scored 14 on reading documents. Runs on a Mac with 64 GB.
Reviews
Reka Edge review: not one we'd recommend right now
It scored 8 out of 100, #54 of 56. It solved 0 of 30 coding jobs and scored 16 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Llama 3.2 1B Instruct (Q4, Mac) review: not one we'd recommend right now
It scored 5 out of 100, #56 of 56. It solved 0 of 30 coding jobs and scored 9 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Why we don't publish speed numbers
How fast a model runs depends on your exact computer and app, so any number we gave would be wrong for most people.
News
Q4 or Q8: which version of a model should you download?
What the letters mean, how much quality you give up, and how to pick the right one for your computer.
Guides
How to check how much memory your graphics card or Mac has
The one number that decides which local models you can run, and where to find it on Windows, Mac and Linux.
Guides
How to run a local LLM with Ollama
Install one app, type one command, and you're chatting with an AI model on your own computer. No account needed.
Guides
Qwen3.6 27B review: one of the best local models we've tested
It scored 97 out of 100, #1 of 56. It solved 29 of 30 coding jobs and scored 97 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
gpt-oss-20b review: a solid all-rounder
It scored 88 out of 100, #7 of 56. It solved 27 of 30 coding jobs and scored 87 on reading documents. Runs on a 16 GB graphics card or a Mac with 24 GB.
Reviews
Qwen3.5-27B review: a solid all-rounder
It scored 88 out of 100, #8 of 56. It solved 23 of 30 coding jobs and scored 100 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3.8 27B review: a solid all-rounder
It scored 88 out of 100, #9 of 56. It solved 23 of 30 coding jobs and scored 99 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3.5-35B-A3B review: a solid all-rounder
It scored 88 out of 100, #10 of 56. It solved 24 of 30 coding jobs and scored 95 on reading documents. Runs on a 24 GB graphics card or a Mac with 48 GB.
Reviews
Qwen3.6 35B A3B review: a solid all-rounder
It scored 86 out of 100, #11 of 56. It solved 24 of 30 coding jobs and scored 93 on reading documents. Runs on a 24 GB graphics card or a Mac with 48 GB.
Reviews
Nemotron 3 Nano 30B A3B review: a solid all-rounder
It scored 80 out of 100, #13 of 56. It solved 21 of 30 coding jobs and scored 91 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Gemma 4 31B review: great at code, weaker with documents
It scored 79 out of 100, #14 of 56. It solved 28 of 30 coding jobs and scored 65 on reading documents. Runs on a 32 GB graphics card or a Mac with 48 GB.
Reviews
Granite 4.2 8B review: decent, with trade-offs
It scored 77 out of 100, #15 of 56. It solved 23 of 30 coding jobs and scored 78 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Qwen3 30B A3B review: decent, with trade-offs
It scored 77 out of 100, #16 of 56. It solved 20 of 30 coding jobs and scored 87 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3 VL 30B A3B Thinking review: reads documents well, weaker at code
It scored 77 out of 100, #17 of 56. It solved 18 of 30 coding jobs and scored 93 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3 14B review: decent, with trade-offs
It scored 72 out of 100, #20 of 56. It solved 19 of 30 coding jobs and scored 81 on reading documents. Runs on a 12 GB graphics card or a Mac with 24 GB.
Reviews
GLM 4.7 Flash review: decent, with trade-offs
It scored 72 out of 100, #21 of 56. It solved 22 of 30 coding jobs and scored 70 on reading documents. Runs on a 24 GB graphics card or a Mac with 48 GB.
Reviews
Qwen3.5-9B review: reads documents well, weaker at code
It scored 72 out of 100, #22 of 56. It solved 14 of 30 coding jobs and scored 97 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Gemma 4 26B A4B review: decent, with trade-offs
It scored 70 out of 100, #23 of 56. It solved 25 of 30 coding jobs and scored 58 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3 32B review: decent, with trade-offs
It scored 64 out of 100, #24 of 56. It solved 15 of 30 coding jobs and scored 79 on reading documents. Runs on a 24 GB graphics card or a Mac with 48 GB.
Reviews
Nemotron 3.5 Lightning review: not one we'd recommend right now
It scored 57 out of 100, #26 of 56. It solved 13 of 30 coding jobs and scored 72 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3 Coder 30B A3B Instruct review: not one we'd recommend right now
It scored 51 out of 100, #30 of 56. It solved 17 of 30 coding jobs and scored 46 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3 VL 30B A3B Instruct review: not one we'd recommend right now
It scored 46 out of 100, #32 of 56. It solved 13 of 30 coding jobs and scored 49 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Ministral 3 14B 2512 review: not one we'd recommend right now
It scored 44 out of 100, #35 of 56. It solved 13 of 30 coding jobs and scored 45 on reading documents. Runs on a 12 GB graphics card or a Mac with 16 GB.
Reviews
Mistral Small 3.2 24B review: not one we'd recommend right now
It scored 44 out of 100, #36 of 56. It solved 12 of 30 coding jobs and scored 47 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Mistral Small 3 review: not one we'd recommend right now
It scored 41 out of 100, #37 of 56. It solved 11 of 30 coding jobs and scored 45 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Gemma 3 27B review: not one we'd recommend right now
It scored 40 out of 100, #38 of 56. It solved 10 of 30 coding jobs and scored 46 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3 30B A3B Instruct 2507 review: not one we'd recommend right now
It scored 40 out of 100, #39 of 56. It solved 10 of 30 coding jobs and scored 46 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Qwen3 VL 8B Instruct review: not one we'd recommend right now
It scored 39 out of 100, #40 of 56. It solved 11 of 30 coding jobs and scored 41 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Ministral 3 8B 2512 review: not one we'd recommend right now
It scored 37 out of 100, #42 of 56. It solved 9 of 30 coding jobs and scored 43 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Gemma 3 12B review: not one we'd recommend right now
It scored 35 out of 100, #43 of 56. It solved 9 of 30 coding jobs and scored 40 on reading documents. Runs on a 12 GB graphics card or a Mac with 16 GB.
Reviews
Phi 4 review: not one we'd recommend right now
It scored 25 out of 100, #44 of 56. It solved 7 of 30 coding jobs and scored 26 on reading documents. Runs on a 12 GB graphics card or a Mac with 24 GB.
Reviews
Qwen2.5 7B Instruct review: not one we'd recommend right now
It scored 24 out of 100, #45 of 56. It solved 3 of 30 coding jobs and scored 37 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Gemma 2 27B review: not one we'd recommend right now
It scored 23 out of 100, #46 of 56. It solved 4 of 30 coding jobs and scored 34 on reading documents. Runs on a 24 GB graphics card or a Mac with 32 GB.
Reviews
Mistral Nemo review: not one we'd recommend right now
It scored 23 out of 100, #48 of 56. It solved 3 of 30 coding jobs and scored 36 on reading documents. Runs on a 12 GB graphics card or a Mac with 16 GB.
Reviews
Ministral 3 3B 2512 review: not one we'd recommend right now
It scored 21 out of 100, #50 of 56. It solved 3 of 30 coding jobs and scored 32 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Llama 3.1 8B Instruct review: not one we'd recommend right now
It scored 15 out of 100, #51 of 56. It solved 1 of 30 coding jobs and scored 26 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Gemma 3 4B review: not one we'd recommend right now
It scored 14 out of 100, #52 of 56. It solved 1 of 30 coding jobs and scored 25 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews
Llama 3.2 3B Instruct review: not one we'd recommend right now
It scored 6 out of 100, #55 of 56. It solved 0 of 30 coding jobs and scored 13 on reading documents. Runs on an 8 GB graphics card or a Mac with 16 GB.
Reviews