VOOZH about

URL: https://willitrunai.com/can-run/hf-intervitens-archive--internlm2-limarp-chat-20b-gguf-on-h100-80gb

⇱ internlm2 limarp chat 20b on NVIDIA H100 80GB? YES

Can internlm2 limarp chat 20b run on NVIDIA H100 80GB?

YES — Runs Great

C48Usable
○Estimated from fit model

internlm2 limarp chat 20b needs ~23.7 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~231 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 23.7 GB, 230.7 tok/s, Runs well
23.7 GB required80.0 GB available
30% VRAM used

Fit status

Runs well

Decode

230.7 tok/s

TTFT

839 ms

Safe context

400K

Memory

23.7 GB / 80.0 GB

Memory breakdown

Weights12.2 GB
KV Cache2.3 GB
Runtime1.2 GB
Headroom8.0 GB

See how fast it feels

See how fast it feelsinternlm2 limarp chat 20b on NVIDIA H100 80GB
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: 230.7 tok/s decode · 839ms TTFT (warm) · 577 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

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well230.7 tok/s458 ms400K
CodingCRuns well230.7 tok/s839 ms400K
Agentic CodingCRuns well230.7 tok/s1221 ms400K
ReasoningCRuns well230.7 tok/s992 ms400K
RAGCRuns well230.7 tok/s1526 ms400K

Quantization options

How internlm2 limarp chat 20b (20B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
7.8 GB
LowD40
Q3_K_S
3
9.8 GB
LowD40
NVFP4
4
11.2 GB
MediumD40
Q4_K_M
4
12.2 GB
MediumC40
Q5_K_M
5
14.4 GB
HighC40
Q6_K
6
16.4 GB
HighC41
Q8_0
8
21.4 GB
Very HighC42
F16Best for your GPU
16
41.0 GB
MaximumC46

Get started

Copy-paste commands to run internlm2 limarp chat 20b on your machine.

Run

lms load hf-intervitens-archive--internlm2-limarp-chat-20b-gguf && lms server start

Frequently asked questions

See all results for NVIDIA H100 80GBSee all hardware for internlm2 limarp chat 20b