Can GGUF SOLARized GraniStral 14B 1902 YeAM HCT run on NVIDIA H20 96GB?

YES — Runs Great

C46Usable

Estimated from fit model

GGUF SOLARized GraniStral 14B 1902 YeAM HCT needs ~21.0 GB VRAM. NVIDIA H20 96GB has 96.0 GB. With Q4_K_M quantization, expect ~196 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) — 21.0 GB, 196.0 tok/s, Runs well

21.0 GB required96.0 GB available

22% VRAM used

Fit status

Runs well

Decode

196.0 tok/s

TTFT

988 ms

Safe context

748K

Memory

21.0 GB / 96.0 GB

Memory breakdown

Weights8.5 GB

KV Cache1.6 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsGGUF SOLARized GraniStral 14B 1902 YeAM HCT on NVIDIA H20 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: 196.0 tok/s decode · 988ms TTFT (warm) · 490 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	196.0 tok/s	539 ms	748K
Coding	C	Runs well	196.0 tok/s	988 ms	748K
Agentic Coding	C	Runs well	196.0 tok/s	1437 ms	748K
Reasoning	C	Runs well	196.0 tok/s	1167 ms	748K
RAG	C	Runs well	196.0 tok/s	1796 ms	748K

Quantization options

How GGUF SOLARized GraniStral 14B 1902 YeAM HCT (14B params) fits at each quantization level on NVIDIA H20 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	D39
Q3_K_S	3	6.9 GB	Low	D39
NVFP4	4	7.8 GB	Medium	D39
Q4_K_M	4	8.5 GB	Medium	D39
Q5_K_M	5	10.1 GB	High	D39
Q6_K	6	11.5 GB	High	D39
Q8_0	8	15.0 GB	Very High	D39
F16Best for your GPU	16	28.7 GB	Maximum	C41

Get started

Copy-paste commands to run GGUF SOLARized GraniStral 14B 1902 YeAM HCT on your machine.

Run

lms load hf-srs6901--gguf-solarized-granistral-14b-1902-yeam-hct && lms server start

Frequently asked questions

Can NVIDIA H20 96GB run GGUF SOLARized GraniStral 14B 1902 YeAM HCT?

Yes, NVIDIA H20 96GB can run GGUF SOLARized GraniStral 14B 1902 YeAM HCT with a C grade (Runs well). Expected decode speed: 196.0 tok/s.

How much VRAM does GGUF SOLARized GraniStral 14B 1902 YeAM HCT need?

GGUF SOLARized GraniStral 14B 1902 YeAM HCT (14B parameters) requires approximately 21.0 GB of memory with Q4_K_M quantization.

What is the best quantization for GGUF SOLARized GraniStral 14B 1902 YeAM HCT?

The recommended quantization for GGUF SOLARized GraniStral 14B 1902 YeAM HCT is Q4_K_M, which balances quality and memory efficiency.

What speed will GGUF SOLARized GraniStral 14B 1902 YeAM HCT run at on NVIDIA H20 96GB?

On NVIDIA H20 96GB, GGUF SOLARized GraniStral 14B 1902 YeAM HCT achieves approximately 196.0 tokens per second decode speed with a time-to-first-token of 988ms using Q4_K_M quantization.

Can NVIDIA H20 96GB run GGUF SOLARized GraniStral 14B 1902 YeAM HCT for coding?

For coding workloads, GGUF SOLARized GraniStral 14B 1902 YeAM HCT on NVIDIA H20 96GB receives a C grade with 196.0 tok/s and 748K context.

What context window can GGUF SOLARized GraniStral 14B 1902 YeAM HCT use on NVIDIA H20 96GB?

On NVIDIA H20 96GB, GGUF SOLARized GraniStral 14B 1902 YeAM HCT can safely use up to 748K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA H20 96GB See all hardware for GGUF SOLARized GraniStral 14B 1902 YeAM HCT

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-srs6901--gguf-solarized-granistral-14b-1902-yeam-hct-on-h20-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

196.0 tok/s

539 ms

748K

Coding

Runs well

196.0 tok/s

988 ms

748K

Agentic Coding

Runs well

196.0 tok/s

1437 ms

748K

Reasoning

Runs well

196.0 tok/s

1167 ms

748K

RAG

Runs well

196.0 tok/s

1796 ms

748K

Quantization options

How GGUF SOLARized GraniStral 14B 1902 YeAM HCT (14B params) fits at each quantization level on NVIDIA H20 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	D39
Q3_K_S	3	6.9 GB	Low	D39
NVFP4	4	7.8 GB	Medium	D39
Q4_K_M	4	8.5 GB	Medium	D39
Q5_K_M	5	10.1 GB	High	D39
Q6_K	6	11.5 GB	High	D39
Q8_0	8	15.0 GB	Very High	D39
F16Best for your GPU	16	28.7 GB	Maximum	C41