PI
Prime Intellect
Language model · United States ·Jan 2025

INTELLECT-MATH

Language Open (Restricted)
7B
Parameters
2
Benchmarks

About INTELLECT-MATH

INTELLECT-MATH is an AI model developed by Prime Intellect, in the language category, released in 2025, made available as an open-weights model with 7B params.

On this page you'll find INTELLECT-MATH's full specifications, including 2 benchmark results. Review provider pricing and benchmark scores below, or compare INTELLECT-MATH head-to-head with other language models.

→ More models by Prime Intellect → All language models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run INTELLECT-MATH locally — what to buy

Share this build ↗

Sized to what INTELLECT-MATH actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
Intel Arc B580 12GB
Consumer GPU · ~$249
~83.8 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
Intel Arc A770 16GB
Consumer GPU · ~$329
~102.9 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
AMD Radeon RX 7800 XT
Consumer GPU · ~$499
~120 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
41.1–120+ tok/s
32 options →
Apple
24.9–120+ tok/s
18 options →
Datacenter GPU
120+ tok/s
13 options →

Community

Would you run INTELLECT-MATH again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

INTELLECT-MATH benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
AIME 2024 math 26.7% step-255-from-hf-readme
MATH-500 math 82% step-255-from-hf-readme

More models like INTELLECT-MATH

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is INTELLECT-MATH? ▶

INTELLECT-MATH is an AI model developed by Prime Intellect, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created INTELLECT-MATH? ▶

INTELLECT-MATH was developed by Prime Intellect and released in 2025.

Is INTELLECT-MATH open source or proprietary? ▶

INTELLECT-MATH ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does INTELLECT-MATH cost? ▶

Pricing for INTELLECT-MATH depends on the provider. See the providers table on this page for the latest API rates.

How does INTELLECT-MATH perform on benchmarks? ▶

INTELLECT-MATH is benchmarked across 2 evaluations on GenAIList, including AIME 2024 (26.7%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about INTELLECT-MATH?