VOOZH about

URL: https://willitrunai.com/can-run/hf-bartowski--internlm2-5-20b-chat-gguf-on-arc-pro-b60-24gb

⇱

Can internlm2 5 20b chat run on Intel Arc Pro B60 24GB?

YES — Runs Great

C52Usable
○Estimated from fit model

internlm2 5 20b chat needs ~17.8 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~20 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: 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) — 17.8 GB, 20.2 tok/s, Runs well
17.8 GB required24.0 GB available
74% VRAM used

Fit status

Runs well

Decode

20.2 tok/s

TTFT

9592 ms

Safe context

58K

Memory

17.8 GB / 24.0 GB

Memory breakdown

Weights12.2 GB
KV Cache2.3 GB
Runtime0.9 GB
Headroom2.4 GB

See how fast it feels

See how fast it feelsinternlm2 5 20b chat on Intel Arc Pro B60 24GB
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: 20.2 tok/s decode · 9.6s TTFT (warm) · 51 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 well20.2 tok/s5232 ms58K
CodingCRuns well20.2 tok/s9592 ms58K
Agentic CodingCTight fit20.2 tok/s13952 ms58K
ReasoningCRuns well20.2 tok/s11336 ms58K
RAGCTight fit20.2 tok/s17440 ms58K

Quantization options

How internlm2 5 20b chat (20B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
7.8 GB
LowC47
Q3_K_S
3
9.8 GB
LowC48
NVFP4
4

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

Upgrade options

Hardware that runs internlm2 5 20b chat well

👁 NVIDIA
RTX 5090 32GBBudget pick
32 GB VRAM (+8)1792 GB/s (+1336)
C
Raises estimated decode speed by about 344%.89.7 tok/s decode

Raises estimated decode speed by about 344%.

Adds memory headroom for longer context windows and future model growth.

This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.

~$1,999 MSRP

MacBook Pro M4 Max 36GBBest value
36 GB Unified (+12)
C
Raises estimated decode speed by about 40%.28.3 tok/s decode

Raises estimated decode speed by about 40%.

~$2,499 MSRP

Frequently asked questions

See all results for Intel Arc Pro B60 24GBSee all hardware for internlm2 5 20b chat
11.2 GB
Medium
C49
Q4_K_M
4
12.2 GB
MediumC50
Q5_K_M
5
14.4 GB
HighC50
Q6_KBest for your GPU
6
16.4 GB
HighC49
Q8_0
8
21.4 GB
Very HighF0
F16
16
41.0 GB
MaximumF0

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.