96 GB VRAM (+16)4000 GB/s (+650)
C
Raises estimated decode speed by about 39%.53.1 tok/s decode
Raises estimated decode speed by about 39%.
~$12,000 MSRP
Can Solar Open 100B run on NVIDIA H100 80GB?
YES — With Offload
C51Usable
○Estimated from fit model
Solar Open 100B needs ~81.6 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~38 tok/s.
Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload
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) — 81.6 GB, 38.1 tok/s, Runs with offload (needs ~1.2 GB host RAM)
81.6 GB required80.0 GB available
102% VRAM needed
1.6 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~1.2 GB host RAM)
Decode
38.1 tok/s
TTFT
5086 ms
Safe context
14K
Memory
81.6 GB / 80.0 GB
Memory breakdown
Weights61.0 GB
KV Cache11.7 GB
Runtime0.9 GB
Headroom8.0 GB
See how fast it feels
See how fast it feelsSolar Open 100B on NVIDIA H100 80GB
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: 38.1 tok/s decode · 5.1s TTFT (warm) · 95 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Best improvement path
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Tight fit | 46.1 tok/s | 2289 ms | 14K |
| Coding | C | Runs with offload | 38.1 tok/s | 5086 ms | 14K |
| Agentic Coding | C | Very compromised (needs ~8.7 GB host RAM) | 30.5 tok/s | 9230 ms | 14K |
| Reasoning | C | Runs with offload (needs ~1.2 GB host RAM) | 38.1 tok/s | 6010 ms | 14K |
| RAG | C | Very compromised (needs ~8.7 GB host RAM) | 30.5 tok/s | 11538 ms |
Quantization options
How Solar Open 100B (100B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 39.0 GB | Low | C47 |
Q3_K_S | 3 | 49.0 GB | Low | C48 |
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 (+61)4800 GB/s (+1450)
C
Raises estimated decode speed by about 73%.66.1 tok/s decode
Raises estimated decode speed by about 73%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
141 GB VRAM (+61)4800 GB/s (+1450)
C
Raises estimated decode speed by about 73%.66.1 tok/s decode
Raises estimated decode speed by about 73%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP