TU
Tsinghua University
Multimodal model · China ·Sep 2024

Oryx 34B

Multimodal Open (Restricted)
34B
Parameters

About Oryx 34B

Oryx 34B is an AI model developed by Tsinghua University, in the multimodal category, released in 2024, made available as an open-weights model with 34B params.

On this page you'll find Oryx 34B's full specifications. Review provider pricing and benchmark scores below, or compare Oryx 34B head-to-head with other multimodal models.

→ More models by Tsinghua University → All multimodal models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run Oryx 34B locally — what to buy

Share this build ↗

Sized to what Oryx 34B 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
AMD Radeon RX 7900 XTX
Consumer GPU · ~$999
~38.8 tok/s
Q4 · tight on context · up to 6k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
NVIDIA GeForce RTX 4090
Consumer GPU · ~$1,599
~46.1 tok/s
Q4 · tight on context · up to 6k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5090
Consumer GPU · ~$1,999
~81.9 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
10.4–81.9 tok/s
9 options →
Apple
12.9–34.5 tok/s
17 options →
Datacenter GPU
34.9–120+ tok/s
13 options →

Community

Would you run Oryx 34B 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 Oryx 34B

AI
NeuroChess
· 72.3K
 TU
GLM-Z1-Rumination-32B-0414
Tsinghua University · 32B
 TU
GLM-4-9B-0414
Tsinghua University · 9B
 TU
Eurus-2-7B-PRIME
Tsinghua University · 7B
 TU
Uni-Med
Tsinghua University · 8.8B
 TU
RDT-1B
Tsinghua University · 1.2B

Frequently asked questions

What is Oryx 34B? ▶

Oryx 34B is an AI model developed by Tsinghua University, in the multimodal category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Oryx 34B? ▶

Oryx 34B was developed by Tsinghua University and released in 2024.

Is Oryx 34B open source or proprietary? ▶

Oryx 34B 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 Oryx 34B cost? ▶

Pricing for Oryx 34B depends on the provider. See the providers table on this page for the latest API rates.

How does Oryx 34B perform on benchmarks? ▶

Benchmark scores for Oryx 34B 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 Oryx 34B?