Choosing a local LLM for reasoning and math? Get a free sizing check.Get a sizing check

OPEN-WEIGHT MODELS · UPDATED NOVEMBER 2026

Best local LLMs for reasoning and mathPicks by GPU size, with scores, VRAM and license

Reasoning models work through science, math and analysis problems step by step before they answer. These are our picks for each size of hardware, with the scores each developer publishes, the GPU memory each model needs and its license.

Our picks by hardware size

ONE GPU · 32 TO 94 GB

Qwen3.8-27B

Qwen · About 24 GB · Apache 2.0

89.2% on GPQA Diamond and 30.8% on Humanity’s Last Exam in about 24 GB of memory, ahead of Qwen3.6-27B (87.8% and 24.0%) and level with Nemotron 3.5 Super VL, which needs about 80 GB.

Qwen3.8-27B hardware requirements →

TWO TO FOUR GPUS · ABOUT 177 GB

DeepSeek-V4-Flash

DeepSeek · About 177 GB · MIT

88.1% on GPQA Diamond, 34.8% on Humanity’s Last Exam and 88.4% on IMO-AnswerBench, under the MIT license with a 1M-token context.

ONE 8-GPU SERVER · ABOUT 455 GB

GLM-5.2

Z.ai · About 455 GB · MIT

99.2% on AIME 2026, 91.0% on IMO-AnswerBench and 40.5% on Humanity’s Last Exam, under the plain MIT license. DeepSeek-V4.1-Flash-1017 scores a little higher on Humanity’s Last Exam (42.6%) but publishes no math scores.

GLM-5.2 hardware requirements →

MORE THAN ONE SERVER · ABOUT 1.64 TB

Kimi K3.1 Pro

Moonshot AI · About 1.64 TB · Kimi K3.1 Pro License

94.2% on GPQA Diamond and 51.1% on Humanity’s Last Exam, the highest open-weight scores listed here. Check its license before commercial use.

Choosing a model for your team?

Tell us your users, your work and your data. We will recommend a model and the hardware to run it inside your own building with Vanik Edge OS. Free, no obligation.

Get a free sizing check

Scores and hardware, model by model

Scores are the ones each developer reports on its own model card, without tools. Where a card lists several reasoning settings, the highest is shown. A dash means the developer has not published that figure.

ModelGPQA DiamondHumanity’s Last ExamAIMEIMO-AnswerBenchMemory, 1 userSmallest setup for 16 usersLicense
Qwen3.6-27B
Qwen model card
87.8%24.0%94.1% (2026)80.8%About 20 GB1 NVIDIA L40SApache 2.0
Gemma 4 31B
Google model card
84.3%19.5%89.2% (2026)—About 20 GB1 NVIDIA L40SApache 2.0
Qwen3.8-27B
Qwen model card
89.2%30.8%——About 24 GB1 NVIDIA L40SApache 2.0
Qwen3.6-35B-A3B
Qwen model card
86.0%21.4%92.7% (2026)78.9%About 24 GB1 NVIDIA L40SApache 2.0
Nemotron 3.5 Super VL
NVIDIA model card
89.9%31.4%——About 80 GB1 NVIDIA RTX PRO 6000 BlackwellOpenMDW 1.1
MiniMax-M2.5
MiniMax model card
85.2%19.4%86.3% (2025)—About 135 GB2 × NVIDIA H100 NVLModified MIT
DeepSeek-V4-Flash
DeepSeek model card
88.1%34.8%—88.4%About 177 GB2 × NVIDIA DGX SparkMIT
GLM-5.2
Z.ai model card
91.2%40.5%99.2% (2026)91.0%About 455 GB4 × NVIDIA H200 NVLMIT
DeepSeek-V4.1-Flash-1017
DeepSeek model card
—42.6%——About 537 GB8 × NVIDIA H100 NVLMIT
Kimi K2.6
Moonshot AI model card
90.5%34.7%96.4% (2026)86.0%About 626 GB8 × NVIDIA H100 NVLModified MIT
DeepSeek-V4-Pro
DeepSeek model card
90.1%37.7%—89.8%About 976 GB8 × NVIDIA H200 NVLMIT
Kimi K3
Moonshot AI model card
93.5%43.5%——About 1.62 TB8 × AMD Instinct MI325XKimi K3 License
Kimi K3.1 Pro
Moonshot AI model card
94.2%51.1%——About 1.64 TB8 × AMD Instinct MI325XKimi K3.1 Pro License

Most of these models need several GPUs working as one. Buying the GPUs is the easy part. Vanik Edge OS splits the model across them, keeps it running if a server fails and manages it all from one console. See how Edge OS clusters GPU servers

What the benchmarks measure

GPQA Diamond. Graduate-level multiple-choice questions in physics, chemistry and biology.

Humanity’s Last Exam. Expert-written questions across many fields, built to be at the edge of what models can answer. Scores are low for every model.

AIME. Problems from the American Invitational Mathematics Examination. The 2025 and 2026 sets are different papers.

IMO-AnswerBench. Olympiad-level math problems with short answers that can be checked.

FROM SIZING TO RUNNING

Sizing the hardware is the easy part.

Getting several GPUs to work as one system for a whole company is where most projects slow down. That is the part Vanik Edge OS does for you.

  1. STEP 01 · THIS TOOL

    Size it

    Work out the GPU memory your models need and which GPUs or servers can hold them.

  2. STEP 02 · VANIK EDGE OS

    Cluster it

    Edge OS joins your GPU servers into one cluster, splits a large model across them and keeps it running if a server fails. NVIDIA and AMD servers work side by side.

  3. STEP 03 · VANIK EDGE OS

    Run it

    Your team gets AI apps with single sign-on and an audit trail, managed from one console, with your data staying inside your building.

See how Edge OS clusters GPU servers

Best local LLMs for reasoning and math: questions

What is the best local LLM for reasoning?

On a single GPU, Qwen3.8-27B. On two to four GPUs, DeepSeek-V4-Flash. On one 8-GPU server, GLM-5.2. With more than one server, Kimi K3.1 Pro, at 94.2% on GPQA Diamond.

What is the best local LLM for math?

GLM-5.2 has the highest published math scores here: 99.2% on AIME 2026 and 91.0% on IMO-AnswerBench. On a single GPU, Qwen3.6-27B scores 94.1% on AIME 2026.

Do reasoning models need more GPU memory?

Not for the weights, but they write long chains of thinking tokens before the answer, which fills the context and takes longer. Plan for a larger context per user and slower replies at the highest reasoning setting.

Why is gpt-oss-120b not in the table?

Its model card on Hugging Face does not publish benchmark figures, and this table only uses figures from each model’s own card. It is still a sound choice for text reasoning on one 80 GB-class GPU.

Can I turn reasoning off to save time?

On most of these models, yes. DeepSeek-V4-Pro, for example, scores 90.1% on GPQA Diamond at its highest setting and 72.9% with thinking off. Use the lower setting for simple questions and the higher one for hard problems.

Where do these scores come from?

Each developer’s own model card, linked in the table. We did not run the benchmarks ourselves, and developers use different test settings, so small differences between models are not meaningful.