16 GB VRAM (+6)896 GB/s (+136)
B
Adds memory headroom for longer context windows and future model growth.87.9 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$749 MSRP
Can solar finalised finetuned Model 10.7B i1 run on RTX 3080 10GB?
YES — With Offload
C53Usable
○Estimated from fit model
solar finalised finetuned Model 10.7B i1 needs ~10.0 GB VRAM. RTX 3080 10GB has 10.0 GB. With Q4_K_M quantization, expect ~89 tok/s.
Runtime: OllamaCapacity: OffloadBandwidth: MediumStack: 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) — 10.0 GB, 88.5 tok/s, Runs with offload
10.0 GB required10.0 GB available
100% VRAM used
Fit status
Runs with offload
Decode
88.5 tok/s
TTFT
2188 ms
Safe context
16K
Memory
10.0 GB / 10.0 GB
Memory breakdown
Weights6.5 GB
KV Cache1.3 GB
Runtime1.2 GB
Headroom1.0 GB
See how fast it feels
See how fast it feelssolar finalised finetuned Model 10.7B i1 on RTX 3080 10GB
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: 88.5 tok/s decode · 2.2s TTFT (warm) · 221 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 | 88.5 tok/s | 1193 ms | 16K |
| Coding | C | Runs with offload | 88.5 tok/s | 2188 ms | 16K |
| Agentic Coding | C | Very compromised (needs ~0.7 GB host RAM) | 51.9 tok/s | 5421 ms | 16K |
| Reasoning | C | Runs with offload | 88.5 tok/s | 2585 ms | 16K |
| RAG | C | Very compromised (needs ~0.7 GB host RAM) | 51.9 tok/s | 6777 ms | 16K |
Quantization options
How solar finalised finetuned Model 10.7B i1 (10.699999809265137B params) fits at each quantization level on RTX 3080 10GB (10.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 4.2 GB | Low | C53 |
Q3_K_S | 3 | 5.2 GB | Low | C52 |
NVFP4 | 4 | 6.0 GB | Medium | C52 |
Q4_K_MBest for your GPU | 4 | 6.5 GB | Medium | C52 |
Q5_K_M | 5 | 7.7 GB | High | F0 |
Q6_K | 6 | 8.8 GB | High | F0 |
Q8_0 | 8 | 11.4 GB | Very High | F0 |
F16 | 16 | 21.9 GB | Maximum | F0 |
Get started
Copy-paste commands to run solar finalised finetuned Model 10.7B i1 on your machine.
Run
lms load hf-mradermacher--solar-finalised-finetuned-model-10-7b-i1-gguf && lms server startUpgrade options