Will It Run AI

Can internlm2 5 20b chat run on Gaudi 3 128GB?

YES — Runs Great

C46Usable
Estimated from fit model

internlm2 5 20b chat needs ~28.2 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~212 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: 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) — 28.2 GB, 212.3 tok/s, Runs well
28.2 GB required128.0 GB available
22% VRAM used

Fit status

Runs well

Decode

212.3 tok/s

TTFT

912 ms

Safe context

697K

Memory

28.2 GB / 128.0 GB

Memory breakdown

Weights12.2 GB
KV Cache2.3 GB
Runtime0.9 GB
Headroom12.8 GB

See how fast it feels

See how fast it feelsinternlm2 5 20b chat on Gaudi 3 128GB
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: 212.3 tok/s decode · 912ms TTFT (warm) · 531 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well212.3 tok/s497 ms697K
CodingCRuns well212.3 tok/s912 ms697K
Agentic CodingCRuns well212.3 tok/s1326 ms697K
ReasoningCRuns well212.3 tok/s1078 ms697K
RAGCRuns well212.3 tok/s1658 ms697K

Quantization options

How internlm2 5 20b chat (20B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
7.8 GB
LowD38
Q3_K_S
3
9.8 GB
LowD38
NVFP4
4
11.2 GB
MediumD38
Q4_K_M
4
12.2 GB
MediumD38
Q5_K_M
5
14.4 GB
HighD38
Q6_K
6
16.4 GB
HighD38
Q8_0
8
21.4 GB
Very HighD39
F16Best for your GPU
16
41.0 GB
MaximumC42

Get started

Copy-paste commands to run internlm2 5 20b chat on your machine.

Run

lms load hf-bartowski--internlm2-5-20b-chat-gguf && lms server start

Frequently asked questions

Can Gaudi 3 128GB run internlm2 5 20b chat?

Yes, Gaudi 3 128GB can run internlm2 5 20b chat with a C grade (Runs well). Expected decode speed: 212.3 tok/s.

How much VRAM does internlm2 5 20b chat need?

internlm2 5 20b chat (20B parameters) requires approximately 28.2 GB of memory with Q4_K_M quantization.

What is the best quantization for internlm2 5 20b chat?

The recommended quantization for internlm2 5 20b chat is Q4_K_M, which balances quality and memory efficiency.

What speed will internlm2 5 20b chat run at on Gaudi 3 128GB?

On Gaudi 3 128GB, internlm2 5 20b chat achieves approximately 212.3 tokens per second decode speed with a time-to-first-token of 912ms using Q4_K_M quantization.

Can Gaudi 3 128GB run internlm2 5 20b chat for coding?

For coding workloads, internlm2 5 20b chat on Gaudi 3 128GB receives a C grade with 212.3 tok/s and 697K context.

What context window can internlm2 5 20b chat use on Gaudi 3 128GB?

On Gaudi 3 128GB, internlm2 5 20b chat can safely use up to 697K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if internlm2 5 20b chat feels slow on Gaudi 3 128GB?

Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Would CUDA be a better path than Gaudi 3 128GB for internlm2 5 20b chat?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Gaudi 3 128GBSee all hardware for internlm2 5 20b chat
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-bartowski--internlm2-5-20b-chat-gguf-on-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: