AS
AI Singapore
Multimodal model · Singapore ·Aug 2025

Gemma-SEA-LION-v4-27B-IT

Multimodal Open (Restricted)
27B
Parameters

About Gemma-SEA-LION-v4-27B-IT

Gemma-SEA-LION-v4-27B-IT is an AI model developed by AI Singapore, in the multimodal category, released in 2025, made available as an open-weights model with 27B params.

On this page you'll find Gemma-SEA-LION-v4-27B-IT's full specifications. Review provider pricing and benchmark scores below, or compare Gemma-SEA-LION-v4-27B-IT head-to-head with other multimodal models.

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

Links

Announcement ↗ Hugging Face ↗

Run Gemma-SEA-LION-v4-27B-IT locally — what to buy

Share this build ↗

Sized to what Gemma-SEA-LION-v4-27B-IT 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
~40.7 tok/s
Q4 · tight on context · up to 7k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
AMD Radeon RX 7900 XTX
Consumer GPU · ~$999
~48.9 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
~103.1 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
13–103.1 tok/s
10 options →
Apple
16.3–43.4 tok/s
17 options →
Datacenter GPU
44–120+ tok/s
13 options →

Community

Would you run Gemma-SEA-LION-v4-27B-IT 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 Gemma-SEA-LION-v4-27B-IT

AI
NeuroChess
· 72.3K
 AS
SEA-LION V3 Llama3.1 70B
AI Singapore · 70B
 AS
SEA-LION V3 Gemma2 9B
AI Singapore · 9B
 AS
SEA-LION V3 Llama3.1 8B
AI Singapore · 8B
 AS
SEA-LION-v1-7B-IT
AI Singapore · 7.5B
 AS
Llama SEA-LION V2 8B
AI Singapore · 8B

Frequently asked questions

What is Gemma-SEA-LION-v4-27B-IT? ▶

Gemma-SEA-LION-v4-27B-IT is an AI model developed by AI Singapore, in the multimodal category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Gemma-SEA-LION-v4-27B-IT? ▶

Gemma-SEA-LION-v4-27B-IT was developed by AI Singapore and released in 2025.

Is Gemma-SEA-LION-v4-27B-IT open source or proprietary? ▶

Gemma-SEA-LION-v4-27B-IT 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 Gemma-SEA-LION-v4-27B-IT cost? ▶

Pricing for Gemma-SEA-LION-v4-27B-IT depends on the provider. See the providers table on this page for the latest API rates.

How does Gemma-SEA-LION-v4-27B-IT perform on benchmarks? ▶

Benchmark scores for Gemma-SEA-LION-v4-27B-IT 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 Gemma-SEA-LION-v4-27B-IT?