Can solar finalised finetuned Model 10.7B i1 run on NVIDIA L20 48GB?

YES — Runs Great

C48Usable

Estimated from fit model

solar finalised finetuned Model 10.7B i1 needs ~13.8 GB VRAM. NVIDIA L20 48GB has 48.0 GB. With Q4_K_M quantization, expect ~97 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: Balanced

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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 13.8 GB, 96.6 tok/s, Runs well

13.8 GB required48.0 GB available

29% VRAM used

Fit status

Runs well

Decode

96.6 tok/s

TTFT

2003 ms

Safe context

453K

Memory

13.8 GB / 48.0 GB

Memory breakdown

Weights6.5 GB

KV Cache1.3 GB

Runtime1.2 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelssolar finalised finetuned Model 10.7B i1 on NVIDIA L20 48GB
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: 96.6 tok/s decode · 2.0s TTFT (warm) · 242 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	96.6 tok/s	1093 ms	453K
Coding	C	Runs well	96.6 tok/s	2003 ms	453K
Agentic Coding	C	Runs well	96.6 tok/s	2914 ms	453K
Reasoning	C	Runs well	96.6 tok/s	2368 ms	453K
RAG	C	Runs well	96.6 tok/s	3643 ms	453K

Quantization options

How solar finalised finetuned Model 10.7B i1 (10.699999809265137B params) fits at each quantization level on NVIDIA L20 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	4.2 GB	Low	C41
Q3_K_S	3	5.2 GB	Low	C41
NVFP4	4	6.0 GB	Medium	C42
Q4_K_M	4	6.5 GB	Medium	C42
Q5_K_M	5	7.7 GB	High	C42
Q6_K	6	8.8 GB	High	C42
Q8_0	8	11.4 GB	Very High	C43
F16Best for your GPU	16	21.9 GB	Maximum	C46

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 start

Frequently asked questions

Can NVIDIA L20 48GB run solar finalised finetuned Model 10.7B i1?

Yes, NVIDIA L20 48GB can run solar finalised finetuned Model 10.7B i1 with a C grade (Runs well). Expected decode speed: 96.6 tok/s.

How much VRAM does solar finalised finetuned Model 10.7B i1 need?

solar finalised finetuned Model 10.7B i1 (10.699999809265137B parameters) requires approximately 13.8 GB of memory with Q4_K_M quantization.

What is the best quantization for solar finalised finetuned Model 10.7B i1?

The recommended quantization for solar finalised finetuned Model 10.7B i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will solar finalised finetuned Model 10.7B i1 run at on NVIDIA L20 48GB?

On NVIDIA L20 48GB, solar finalised finetuned Model 10.7B i1 achieves approximately 96.6 tokens per second decode speed with a time-to-first-token of 2003ms using Q4_K_M quantization.

Can NVIDIA L20 48GB run solar finalised finetuned Model 10.7B i1 for coding?

For coding workloads, solar finalised finetuned Model 10.7B i1 on NVIDIA L20 48GB receives a C grade with 96.6 tok/s and 453K context.

What context window can solar finalised finetuned Model 10.7B i1 use on NVIDIA L20 48GB?

On NVIDIA L20 48GB, solar finalised finetuned Model 10.7B i1 can safely use up to 453K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA L20 48GB See all hardware for solar finalised finetuned Model 10.7B i1

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/hf-mradermacher--solar-finalised-finetuned-model-10-7b-i1-gguf-on-l20-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: