Solar Open 100B NotaMoEQuant NVFP4 — Hardware Requirements & GPU Compatibility
Chat
Solar Open 100B NotaMoEQuant NVFP4 is a 59.3B-parameter open language model from nota-ai in the Solar family. It supports a context window of up to 131,072 tokens. At BF16 it needs about 119.19 GB of VRAM — see which GPUs and Macs can run it below.
163 downloads
3 likesSpecifications
- Publisher
- nota-ai
- Family
- Solar
- Parameters
- 59.3B
- Architecture
- SolarOpenForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 196,608
- Release Date
- 2026-03-11
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Solar Open 100B NotaMoEQuant NVFP4 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 119.2 GB | 131.9 GB | 118.69 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Solar Open 100B NotaMoEQuant NVFP4?
BF16 · 119.2 GBSolar Open 100B NotaMoEQuant NVFP4 (BF16) requires 119.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 155+ GB is recommended. Using the full 131K context window can add up to 12.7 GB, bringing total usage to 131.9 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Solar Open 100B NotaMoEQuant NVFP4?
BF16 · 119.2 GB5 devices with unified memory can run Solar Open 100B NotaMoEQuant NVFP4, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (128 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Solar Open 100B NotaMoEQuant NVFP4 need?
Solar Open 100B NotaMoEQuant NVFP4 requires 119.2 GB of VRAM at BF16. Full 131K context adds up to 12.7 GB (131.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 59.3B × 16 bits ÷ 8 = 118.7 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 13.2 GB (at full 131K context)
VRAM usage by quantization
BF16119.2 GBBF16 + full context131.9 GB- Can NVIDIA GeForce RTX 5090 run Solar Open 100B NotaMoEQuant NVFP4?
No — Solar Open 100B NotaMoEQuant NVFP4 requires at least 119.2 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Solar Open 100B NotaMoEQuant NVFP4 on a Mac?
Solar Open 100B NotaMoEQuant NVFP4 requires at least 119.2 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Solar Open 100B NotaMoEQuant NVFP4 locally?
Yes — Solar Open 100B NotaMoEQuant NVFP4 can run locally on consumer hardware. At BF16 quantization it needs 119.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Solar Open 100B NotaMoEQuant NVFP4?
At BF16, Solar Open 100B NotaMoEQuant NVFP4 can reach ~25 tok/s on AMD Instinct MI300X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 119.2 × 0.55 = ~25 tok/s
Estimated speed at BF16 (119.2 GB)
~25 tok/s~15 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Solar Open 100B NotaMoEQuant NVFP4?
At BF16, the download is about 118.69 GB.
- Which GPUs can run Solar Open 100B NotaMoEQuant NVFP4?
No single consumer GPU has enough VRAM to run Solar Open 100B NotaMoEQuant NVFP4 at BF16 (119.2 GB). Multi-GPU or professional hardware is required.
- Which devices can run Solar Open 100B NotaMoEQuant NVFP4?
5 devices with unified memory can run Solar Open 100B NotaMoEQuant NVFP4 at BF16 (119.2 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), NVIDIA DGX A100 640GB. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.