VOOZH about

URL: https://willitrunai.com/can-run/hf-lgai-exaone--k-exaone-236b-a23b-gguf-on-instinct-mi250x-128gb

⇱ K EXAONE 236B A23B on AMD Instinct MI250X 128GB? No — Alter…

Can K EXAONE 236B A23B run on AMD Instinct MI250X 128GB?

YES — With Q2_K

C48Usable
○Estimated from fit model

K EXAONE 236B A23B needs ~133.4 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q2_K quantization, expect ~16 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: 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.

K EXAONE 236B A23B at Q4_K_M needs 185.3 GB — too much for AMD Instinct MI250X 128GB (128.0 GB). Runs at Q2_K (133.4 GB) with low quality.
Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 185.3 GB, exceeds 128.0 GB available
185.3 GB required128.0 GB available
145% VRAM needed

57.3 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

6.0 tok/s

TTFT

32443 ms

Safe context

4K

Memory

185.3 GB / 128.0 GB

Offload

30%

Memory breakdown

Weights144.0 GB
KV Cache27.7 GB
Runtime0.9 GB
Headroom12.8 GB

See how fast it feels

With memory offload — actual speed may be lower
See how fast it feelsK EXAONE 236B A23B on AMD Instinct MI250X 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: 6.0 tok/s decode · 32.4s TTFT (warm) · 15 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatFToo heavy7.0 tok/s15031 ms4K
CodingFToo heavy6.0 tok/s32443 ms4K
Agentic CodingFToo heavy4.5 tok/s63243 ms4K
ReasoningFToo heavy6.0 tok/s38342 ms4K
RAGFToo heavy4.5 tok/s79054 ms4K

Quantization options

How K EXAONE 236B A23B (236B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

QuantBitsVRAMQualityFit
Q2_KBest for your GPU
2
92.0 GB
LowC48
Q3_K_S
3
115.6 GB
LowF0
NVFP4
4
132.2 GB
MediumF0
Q4_K_M
4
144.0 GB
MediumF0
Q5_K_M
5
169.9 GB
HighF0
Q6_K
6
193.5 GB
HighF0
Q8_0
8
252.5 GB
Very HighF0
F16
16
483.8 GB
MaximumF0

Get started

Copy-paste commands to run K EXAONE 236B A23B on your machine.

Run

lms load hf-lgai-exaone--k-exaone-236b-a23b-gguf && lms server start

Upgrade options

Hardware that runs K EXAONE 236B A23B well

AMD Instinct MI350X 288GBBudget pick
288 GB VRAM (+160)8000 GB/s (+4800)
C
Makes the model fit on the accelerator instead of staying completely out of reach.40.6 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$8,000 MSRP

AMD Instinct MI300X 192GBBest value
192 GB VRAM (+64)5300 GB/s (+2100)
C
Makes the model fit on the accelerator instead of staying completely out of reach.28.7 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$15,000 MSRP

AMD Instinct MI325X 256GBAMD upgrade
256 GB VRAM (+128)6000 GB/s (+2800)
C
Makes the model fit on the accelerator instead of staying completely out of reach.30.4 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$20,000 MSRP

Frequently asked questions

See all results for AMD Instinct MI250X 128GBSee all hardware for K EXAONE 236B A23B