Can InternVL2 8B run on NVIDIA GH200 96GB?

YES — Runs Great

A78Great

○Estimated from fit model

InternVL2 8B needs ~17.6 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~112 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) — 17.6 GB, 112.0 tok/s, Runs well

17.6 GB required96.0 GB available

18% VRAM used

Fit status

Runs well

Decode

112.0 tok/s

TTFT

1729 ms

Safe context

Memory

17.6 GB / 96.0 GB

Memory breakdown

Weights4.9 GB

KV Cache2.0 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsInternVL2 8B on NVIDIA GH200 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: 112.0 tok/s decode · 1.7s TTFT (warm) · 280 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	A	Runs well	112.0 tok/s	943 ms	8K
Coding	A	Runs well	112.0 tok/s	1729 ms	8K
Agentic Coding	A	Runs well	112.0 tok/s	2514 ms	8K
Reasoning	A	Runs well	112.0 tok/s	2043 ms	8K
RAG	A	Runs well	112.0 tok/s	3143 ms	8K

Quantization options

How InternVL2 8B (8B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.1 GB	Low	A71
Q3_K_S	3	3.9 GB	Low	A71
NVFP4	4	4.5 GB	Medium	A71
Q4_K_M	4	4.9 GB	Medium	A71
Q5_K_M	5	5.8 GB	High	A71
Q6_K	6	6.6 GB	High	A71
Q8_0	8	8.6 GB	Very High	A72
F16Best for your GPU	16	16.4 GB	Maximum	A72

Get started

Copy-paste commands to run InternVL2 8B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "OpenGVLab/InternVL2-8B" \
 --hf-file "InternVL2-8B-Q4_K_M.gguf" \
 -c 4096 -ngl 99

Your hardware

More models your NVIDIA GH200 96GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	47 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	489.9 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	212.5 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	213.1 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	130.3 tok/s

Frequently asked questions

See all results for NVIDIA GH200 96GB See all hardware for InternVL2 8B

URL: https://willitrunai.com/can-run/internvl2-8b-on-gh200-96gb