Leaderboard / NAVER (HyperCLOVA X)
HyperCLOVA X SEED Omni 8B
NAVER (HyperCLOVA X) · HyperCLOVA X SEED · released 2025-12-23 · data checked 2026-11-02 Needs verification
HyperCLOVA X SEED Omni 8B is a 10.7B-parameter dense model from NAVER (HyperCLOVA X) (Rest of Asia), released 2025-12-23 under the HyperCLOVA X SEED License license. It doesn't have enough reported benchmarks for an index score yet. It needs about 8.4 GB of memory at 4-bit with an 8K-token context.
Small LM Index
—
Needs 2 core benchmarks (has 0)
Parameters
10.7B
Dense
Price per 1M tokens
—
No hosted API on OpenRouter; self-host
Context window
8K
tokens
Benchmarks
Each bar shows this model's score. The tick marks the best small model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Specifications
- Lab
- NAVER (HyperCLOVA X) (KR · Rest of Asia)
- Architecture
- Dense transformer
- Total parameters
- 10.7B
- Active parameters
- All (dense)
- Size class
- Small
- Context window
- 8K tokens
- Input modalities
- text, image, audio
- Reasoning
- Instruct (no thinking)
- License
- HyperCLOVA X SEED License
- Openness
- Open weights
- Memory to run
- ~8.4 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 1.5K downloads (30 days) · 194 likes
Compare with
- HyperCLOVA X SEED Omni 8B vs Gemma 4 12B (11.9B, index 56.9)
- HyperCLOVA X SEED Omni 8B vs MiniCPM-SALA (9.5B, index 52.6)
- HyperCLOVA X SEED Omni 8B vs Gemma 3 12B (12.2B, index 28.4)
Sources
Something wrong here? Report it.
Run it locally
No GGUF build from a well-known publisher yet.
vLLM (GPU server)
vllm serve naver-hyperclovax/HyperCLOVAX-SEED-Omni-8BFull-precision weights, for a server GPU.
Memory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 8K context |
|---|---|---|
| 16-bit F16 | 23 GB | 23 GB |
| 8-bit Q8_0 | 13 GB | 13 GB |
| 4-bit Q4_K_M | 7.8 GB | 8.4 GB |