NY
New York University (NYU)
Multimodal model · United States ·Jun 2024

Cambrian-1-13B

Multimodal Open (Restricted)
13B
Parameters

About Cambrian-1-13B

Cambrian-1-13B is an AI model developed by New York University (NYU), in the multimodal category, released in 2024, made available as an open-weights model with 13B params.

On this page you'll find Cambrian-1-13B's full specifications. Review provider pricing and benchmark scores below, or compare Cambrian-1-13B head-to-head with other multimodal models.

→ More models by New York University (NYU) → All multimodal models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run Cambrian-1-13B locally — what to buy

Share this build ↗

Sized to what Cambrian-1-13B 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
~45.1 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
~55.4 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 4090
Consumer GPU · ~$1,599
~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
22.2–120+ tok/s
28 options →
Apple
33.8–90.1 tok/s
17 options →
Datacenter GPU
91.4–120+ tok/s
13 options →

Community

Would you run Cambrian-1-13B 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.

More models like Cambrian-1-13B

AI
NeuroChess
· 72.3K
 NY
Cambrian-1-34B
New York University (NYU) · 34B
 NY
Cambrian-1-8B
New York University (NYU) · 8B
 NY
DiT-XL/2
New York University (NYU) · 675M
 NY
NMST+GPT-2
New York University (NYU) · 124M
 NY
Large regularized LSTM
New York University (NYU) · 66M

Frequently asked questions

What is Cambrian-1-13B? ▶

Cambrian-1-13B is an AI model developed by New York University (NYU), in the multimodal category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Cambrian-1-13B? ▶

Cambrian-1-13B was developed by New York University (NYU) and released in 2024.

Is Cambrian-1-13B open source or proprietary? ▶

Cambrian-1-13B 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 Cambrian-1-13B cost? ▶

Pricing for Cambrian-1-13B depends on the provider. See the providers table on this page for the latest API rates.

How does Cambrian-1-13B perform on benchmarks? ▶

Benchmark scores for Cambrian-1-13B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

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

Know a great video about Cambrian-1-13B?