Can LLaVA 1.6 13B run on NVIDIA H200 141GB?

YES — Runs Great

A71Great

○Estimated from fit model

LLaVA 1.6 13B needs ~35.4 GB VRAM. NVIDIA H200 141GB has 141.0 GB. With Q4_K_M quantization, expect ~182 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) — 35.4 GB, 182.0 tok/s, Runs well

35.4 GB required141.0 GB available

25% VRAM used

Fit status

Runs well

Decode

182.0 tok/s

TTFT

1064 ms

Safe context

Memory

35.4 GB / 141.0 GB

Memory breakdown

Weights7.9 GB

KV Cache12.2 GB

Runtime1.2 GB

Headroom14.1 GB

See how fast it feels

See how fast it feelsLLaVA 1.6 13B on NVIDIA H200 141GB
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: 182.0 tok/s decode · 1.1s TTFT (warm) · 455 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	B	Runs well	182.0 tok/s	580 ms	4K
Coding	A	Runs well	182.0 tok/s	1064 ms	4K
Agentic Coding	A	Runs well	182.0 tok/s	1547 ms	4K
Reasoning	A	Runs well	182.0 tok/s	1257 ms	4K
RAG	A	Runs well	182.0 tok/s	1934 ms	4K

Quantization options

How LLaVA 1.6 13B (13B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.1 GB	Low	B61
Q3_K_S	3	6.4 GB	Low	B61
NVFP4	4	7.3 GB	Medium	B61
Q4_K_M	4	7.9 GB	Medium	B61
Q5_K_M	5	9.4 GB	High	B61
Q6_K	6	10.7 GB	High	B61
Q8_0	8	13.9 GB	Very High	B62
F16Best for your GPU	16	26.7 GB	Maximum	B63

Get started

Copy-paste commands to run LLaVA 1.6 13B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "liuhaotian/llava-v1.6-mistral-7b" \
 --hf-file "llava-v1.6-mistral-7b-Q4_K_M.gguf" \
 -c 4096 -ngl 99

Your hardware

More models your NVIDIA H200 141GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	58.4 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	609.7 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	264.4 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	265.2 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	162.1 tok/s

Frequently asked questions

See all results for NVIDIA H200 141GB See all hardware for LLaVA 1.6 13B

URL: https://willitrunai.com/can-run/llava-1.6-13b-on-h200-141gb

⇱ LLaVA 1.6 13B on NVIDIA H200 141GB? YES