141 GB VRAM (+13)4800 GB/s (+4527)
C
Raises estimated decode speed by about 2348%.66.1 tok/s decode
Raises estimated decode speed by about 2348%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Can Solar Open 100B run on NVIDIA DGX Spark 128GB?
YES — Runs Great
C46Usable
○Estimated from fit model
Solar Open 100B needs ~87.0 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~3 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Memory bandwidth
Share:
Operating mode
Choose the run profile you care about
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Q4_K_M (Medium quality) — 87.0 GB, 2.7 tok/s, Runs well
87.0 GB required108.8 GB available
80% VRAM used
Fit status
Runs well
Decode
2.7 tok/s
TTFT
72098 ms
Safe context
46K
Memory
87.0 GB / 108.8 GB
Memory breakdown
Weights61.0 GB
KV Cache11.7 GB
Runtime1.2 GB
Headroom13.1 GB
See how fast it feels
See how fast it feelsSolar Open 100B on NVIDIA DGX Spark 128GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.
When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.
Key benefits of running locally:
- Full privacy: your prompts never leave your machine
- No per-token cost or rate limits
- Works offline once the model is downloaded
- Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:
Model size Q4 (4-bit) Q8 (8-bit) FP16
7B params ~4.3 GB ~7.5 GB ~14 GB
13B params ~7.9 GB ~13.9 GB ~26 GB
70B params ~42.7 GB ~74.9 GB ~140 GB
Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 2.7 tok/s decode · 72.1s TTFT (warm) · 7 tok/s prefill
What limits this setup
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Best improvement path
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 2.7 tok/s | 39326 ms | 46K |
| Coding | C | Runs well | 2.7 tok/s | 72098 ms | 46K |
| Agentic Coding | C | Tight fit | 2.7 tok/s | 104869 ms | 46K |
| Reasoning | C | Runs well | 2.7 tok/s | 85206 ms | 46K |
| RAG | C | Tight fit | 2.7 tok/s | 131087 ms | 46K |
Quantization options
How Solar Open 100B (100B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 39.0 GB | Low | C45 |
Q3_K_S | 3 | 49.0 GB | Low | C48 |
NVFP4 | 4 | 56.0 GB | Medium | C48 |
Q4_K_M | 4 | 61.0 GB | Medium | C48 |
Q5_K_MBest for your GPU | 5 | 72.0 GB | High | C48 |
Q6_K | 6 | 82.0 GB | High | F0 |
Q8_0 | 8 | 107.0 GB | Very High | F0 |
F16 | 16 | 205.0 GB | Maximum | F0 |
Get started
Copy-paste commands to run Solar Open 100B on your machine.
Run
lms load hf-aaryank--solar-open-100b-gguf && lms server startUpgrade options
Hardware that runs Solar Open 100B well
141 GB VRAM (+13)4800 GB/s (+4527)
C
Raises estimated decode speed by about 2348%.66.1 tok/s decode
Raises estimated decode speed by about 2348%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
180 GB VRAM (+52)8000 GB/s (+7727)
C
Raises estimated decode speed by about 3981%.110.2 tok/s decode
Raises estimated decode speed by about 3981%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP