Solar Open 100B — Hardware Requirements & GPU Compatibility
ChatFunctions
Solar Open 100B is a 102.7B-parameter open language model from Upstage in the Solar family. It supports a context window of up to 131,072 tokens. At BF16 it needs about 205.80 GB of VRAM — see which GPUs and Macs can run it below.
Solar Open 100B runs on a 256 GB+ Mac or a datacenter GPU
Best local pick → Mac Studio (M3 Ultra, 256GB) · BF16 · 207.2 GB · ~19 tok/s
Macs from 256 GB (BF16 · ~19 tok/s)
Other
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Solar Open 100B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve upstage/Solar-Open-100B --max-model-len 16384 --tensor-parallel-size 8vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on B300 (288 GB) (80 GB headroom) · BF16
- Generation speed
- ~137 tok/s
- generation speed
- Cost per 1M output tokens
- $14.05
- per 1M output tokens
How Much VRAM Does Solar Open 100B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 205.8 GB | 208.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on Instinct MI325X 256 GB |
Selected BF16
Brain floating point 16207.2GBat 16K context
- Weights
- 205.3 GB
- KV cache
- 1.6 GB
- Overhead
- 0.3 GB
Server-class: ~207.2 GB at 16K context · one Instinct MI325X 256 GB
Or .
Which Hardware Can Run Solar Open 100B?
BF16 · 205.8 GBSolar Open 100B (BF16) requires 205.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 268+ GB is recommended. Using the full 131K context window can add up to 12.7 GB, bringing total usage to 218.5 GB. No consumer GPU has enough memory. 2 devices with unified memory can run Solar Open 100B, including Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 256GB).
Needs server-class hardware
Solar Open 100B runs on a 256 GB+ Mac or a datacenter GPU · BF16 needs ~207.2 GB
| Hardware | Quant | Memory | Speed | Context | Hardware page | |
|---|---|---|---|---|---|---|
| Mac 256 GB · Mac Studio (M3 Ultra, 256GB) | BF16 | 207.2 GB | ~19 tok/s | 128K ctx | Mac Studio → | BF16 · 207.2 GB · ~19 tok/s · 128K ctx |
| Instinct MI325X 256 GB · one GPU | BF16 | 207.2 GB | ~61 tok/s | 128K ctx | Instinct MI325X → | BF16 · 207.2 GB · ~61 tok/s · 128K ctx |
| 3× H100 SXM 80 GB · 240 GB | BF16 | 207.2 GB | — | 64K ctx | H100 SXM → | BF16 · 207.2 GB · 64K ctx |
| 2× H200 SXM 141 GB · 282 GB | BF16 | 207.2 GB | — | 128K ctx | H200 SXM → | BF16 · 207.2 GB · 128K ctx |
| 2× B200 192 GB · 384 GB | BF16 | 207.2 GB | — | 128K ctx | B200 → | BF16 · 207.2 GB · 128K ctx |
Also: Instinct MI325X · Instinct MI350X · Instinct MI355X · B300 · Mac Studio (M3 Ultra, 256GB) · Mac Studio (M3 Ultra, 512GB) · NVIDIA DGX A100 640GB · NVIDIA DGX H100
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 192 GB: too small for this model (needs ≥ 207.2 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llama 4 Scout 17B 16E InstructMeta | 82.1 | 77 GB | —needs > 24 GB | same size |
| GLM 4.6VZ.ai | — | 66 GB | —needs > 24 GB | same size |
| Ring Flash 2.0Inclusion AI | — | 63.1 GB | —needs > 24 GB | same size |
| Ling Flash 2.0Inclusion AI | — | 63.1 GB | —needs > 24 GB | same size |
| C4ai Command R Plus 08 2024Cohere | — | 73.8 GB | —needs > 24 GB | same size |
| Sarvam 105Bsarvamai | — | 238.6 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- Upstage
- Family
- Solar
- Parameters
- 102.7B
- Active parameters
- 12.1B per token
- Architecture
- SolarOpenForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 196,608
- Release Date
- 2025-12-10
- License
- Other
Frequently Asked Questions
How much VRAM does Solar Open 100B need?
Solar Open 100B requires 205.8 GB of VRAM at BF16. Full 131K context adds up to 12.7 GB (218.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 102.7B × 16 bits ÷ 8 = 205.3 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 13.2 GB (at full 131K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Solar Open 100B?
No — Solar Open 100B requires at least 205.8 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Solar Open 100B on a Mac?
Yes — Mac Studio (M3 Ultra, 256GB) and 1 other Mac can run Solar Open 100B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 205.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Solar Open 100B locally?
Yes — Solar Open 100B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Solar Open 100B?
At BF16, Solar Open 100B can reach ~68 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B300 → 24.2 GB active ÷ (8000 × 0.65) = 4.65 ms, plus 48 layers × 0.055 ms = 2.64 ms, so 1000 ÷ 7.29 ms = ~137 tok/s
Estimated speed at BF16 (205.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Solar Open 100B?
At BF16, the download is about 205.30 GB.
Which GPUs can run Solar Open 100B?
No single consumer GPU has enough VRAM to run Solar Open 100B at BF16 (205.8 GB). Multi-GPU or professional hardware is required.
Which devices can run Solar Open 100B?
2 devices with unified memory can run Solar Open 100B at BF16 (205.8 GB), including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.