AL
Alibaba
Multimodal model · China ·Nov 2024

Ovis1.6-Gemma2-27B

Multimodal Open (Restricted)
28.9B
Parameters

About Ovis1.6-Gemma2-27B

Ovis1.6-Gemma2-27B is an AI model developed by Alibaba, in the multimodal category, released in 2024, made available as an open-weights model with 28.9B params.

On this page you'll find Ovis1.6-Gemma2-27B's full specifications. Review provider pricing and benchmark scores below, or compare Ovis1.6-Gemma2-27B head-to-head with other multimodal models.

→ More models by Alibaba → All multimodal models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run Ovis1.6-Gemma2-27B locally — what to buy

Share this build ↗

Sized to what Ovis1.6-Gemma2-27B 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 XT
Consumer GPU · ~$899
~38.1 tok/s
Q4 · tight on context · up to 3k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
AMD Radeon RX 7900 XTX
Consumer GPU · ~$999
~45.7 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5090
Consumer GPU · ~$1,999
~96.3 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
12.2–96.3 tok/s
10 options →
Apple
15.2–40.5 tok/s
17 options →
Datacenter GPU
41.1–120+ tok/s
13 options →

Community

Would you run Ovis1.6-Gemma2-27B 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 Ovis1.6-Gemma2-27B

AI
NeuroChess
· 72.3K
 AL
Qwen3-TTS
Alibaba
 AL
Qwen-Image-Layered
Alibaba
 AL
Qwen3-Omni-Flash (2025-12-01)
Alibaba
 AL
Qwen3-LiveTranslate
Alibaba
 AL
Qwen3-VL (series)
Alibaba

Frequently asked questions

What is Ovis1.6-Gemma2-27B? ▶

Ovis1.6-Gemma2-27B is an AI model developed by Alibaba, in the multimodal category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Ovis1.6-Gemma2-27B? ▶

Ovis1.6-Gemma2-27B was developed by Alibaba and released in 2024.

Is Ovis1.6-Gemma2-27B open source or proprietary? ▶

Ovis1.6-Gemma2-27B 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 Ovis1.6-Gemma2-27B cost? ▶

Pricing for Ovis1.6-Gemma2-27B depends on the provider. See the providers table on this page for the latest API rates.

How does Ovis1.6-Gemma2-27B perform on benchmarks? ▶

Benchmark scores for Ovis1.6-Gemma2-27B 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 Ovis1.6-Gemma2-27B?