dots.llm1.inst 142.8B — 142.8B Parameter Dense LLM
Model Specifications
- Parameters
- 142.8B
- Architecture
- Dense Transformer
- Context Length
- 32K tokens
- Capabilities
- chat
- Release Date
- 2025-05-14
- Provider
- Rednote
- Family
- other
VRAM Requirements
| Quantization | BPW | VRAM | Quality |
|---|---|---|---|
| IQ2_XXS | 2.38 | 43.0 GB | 65% |
| IQ2_M | 2.93 | 52.8 GB | 75% |
| Q2_K | 3.16 | 56.9 GB | 78% |
| IQ3_XXS | 3.25 | 58.5 GB | 82% |
| IQ3_XS | 3.5 | 63.0 GB | 84% |
| Q3_K_S | 3.64 | 65.5 GB | 85% |
| IQ3_M | 3.76 | 67.6 GB | 86% |
| Q3_K_M | 4 | 71.9 GB | 88% |
| Q3_K_L | 4.3 | 77.2 GB | 90% |
| IQ4_XS | 4.46 | 80.1 GB | 92% |
| Q4_K_S | 4.67 | 83.8 GB | 93% |
| Q4_K_M | 4.89 | 87.8 GB | 94% |
| Q5_K_S | 5.57 | 99.9 GB | 96% |
| Q5_K_M | 5.7 | 102.2 GB | 96% |
| Q6_K | 6.56 | 117.6 GB | 97% |
| Q8_0 | 8.5 | 152.2 GB | 100% |
| FP16 | 16 | 286.1 GB | 100% |
How to Run dots.llm1.inst 142.8B
Run dots.llm1.inst 142.8B locally with Ollama (needs 87.8 GB VRAM at Q4_K_M):
ollama run other:142bCompatible GPUs (30)
GPUs that can run dots.llm1.inst 142.8B at Q4_K_M quantization:
NVIDIA B200(90GB, 4100 GB/s)NVIDIA H100 NVL 94 GB(94GB, 3940 GB/s)NVIDIA H100 SXM5 94 GB(94GB, 3360 GB/s)RTX Pro 6000(96GB, 1792 GB/s)NVIDIA H100 PCIe 96 GB(96GB, 3360 GB/s)NVIDIA H100 SXM5 96 GB(96GB, 3360 GB/s)Intel Data Center GPU Max 1350(96GB, 2460 GB/s)NVIDIA RTX PRO 6000 Blackwell Server(96GB, 1790 GB/s)NVIDIA RTX PRO 6000 Blackwell(96GB, 1790 GB/s)AMD Instinct MI300A(120GB, 5300 GB/s)Apple M4 Max (128GB)(128GB, 546 GB/s)AMD Instinct MI250X(128GB, 3277 GB/s)Apple M1 Ultra (128GB)(128GB, 800 GB/s)Apple M2 Ultra (128GB)(128GB, 800 GB/s)AMD Radeon Instinct MI250(128GB, 3280 GB/s)