141 GB VRAM (+45)4800 GB/s (+3203)
C
Raises estimated decode speed by about 200%.66.1 tok/s decode
Raises estimated decode speed by about 200%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Can Solar Open 100B run on RTX PRO 6000 Blackwell Server Edition 96GB?
YES — Tight Fit
C49Usable
○Estimated from fit model
Solar Open 100B needs ~83.5 GB VRAM. RTX PRO 6000 Blackwell Server Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~22 tok/s.
Runtime: OllamaCapacity: TightBandwidth: HighStack: BasicBottleneck: Balanced
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) — 83.5 GB, 22.0 tok/s, Tight fit
83.5 GB required96.0 GB available
87% VRAM used
Fit status
Tight fit
Decode
22.0 tok/s
TTFT
8803 ms
Safe context
33K
Memory
83.5 GB / 96.0 GB
Memory breakdown
Weights61.0 GB
KV Cache11.7 GB
Runtime1.2 GB
Headroom9.6 GB
See how fast it feels
See how fast it feelsSolar Open 100B on RTX PRO 6000 Blackwell Server Edition 96GB
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: 22.0 tok/s decode · 8.8s TTFT (warm) · 55 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 22.0 tok/s | 4802 ms | 33K |
| Coding | C | Tight fit | 22.0 tok/s | 8803 ms | 33K |
| Agentic Coding | C | Runs with offload | 22.0 tok/s | 12805 ms | 33K |
| Reasoning | C | Tight fit | 22.0 tok/s | 10404 ms | 33K |
| RAG | C | Runs with offload | 22.0 tok/s | 16006 ms | 33K |
Quantization options
How Solar Open 100B (100B params) fits at each quantization level on RTX PRO 6000 Blackwell Server Edition 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 39.0 GB | Low | C45 |
Q3_K_S | 3 | 49.0 GB | Low | C47 |
NVFP4 | 4 |
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 (+45)4800 GB/s (+3203)
C
Raises estimated decode speed by about 200%.66.1 tok/s decode
Raises estimated decode speed by about 200%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
180 GB VRAM (+84)8000 GB/s (+6403)
C
Raises estimated decode speed by about 401%.110.2 tok/s decode
Raises estimated decode speed by about 401%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP