SCB 10X · 30.5B (3.3B active) · Mixture of Experts
Thai/English bilingual MoE built on Qwen 3 30B-A3B, 256K context
0 downloads
0 likes
2025-09 256K context
Use Cases
chat multilingual reasoning
Mixture of Experts
Total experts: 128
Active experts: 8
Active params: 3.3B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 10.3 GB | low | — |
| Q3_K_M | 3 | 14.2 GB | moderate | — |
| Q4_K_M | 4 | 16.1 GB | good | — |
| Q5_K_M | 5 | 20 GB | good | — |
| Q6_K | 6 | 23.9 GB | excellent | — |
| Q8_0 | 8 | 31.7 GB | excellent | — |
| F16 | 16 | 63 GB | lossless | — |
GPUs that run Typhoon 2.5 30B-A3B
Typhoon 2.5 30B-A3B needs about 16.1 GB of VRAM at Q4_K_M, so it runs comfortably on a GPU with 20 GB of VRAM or more (39 of the GPUs we track). Common cards, smallest first:
| VRAM | GPUs |
|---|---|
| 20 GB | RTX 4000 SFF Ada , RX 7900 XT , RTX 4000 Ada |
| 24 GB | RTX 4090 , RX 7900 XTX , RTX 3090 Ti |
| 32 GB | RTX 5090 , RTX 5000 Ada , Tesla V100 32GB |
About this model
Typhoon2.5-Qwen3-30B-A3B: Thai Large Language Model (Instruct) - Q4_K_M quantized
Typhoon2.5-Qwen3-30B-A3B is a instruct Thai 🇹🇭 large language model with 30 billion parameters, and it is based on Qwen3 30B-A3B.
By using this model, you agree to the OpenTyphoon Terms and Conditions and acknowledge the Privacy Notice: https://opentyphoon.ai/tac · https://opentyphoon.ai/privacy
Run
ollama run scb10x/typhoon2.5-qwen3-30b-a3b
Performance
