willitrun·ai

Can K EXAONE 236B A23B run on AMD Instinct MI325X 256GB?

YES — Runs Great

C53Usable
Estimated from fit model

K EXAONE 236B A23B needs ~198.1 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q4_K_M quantization, expect ~30 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) — 198.1 GB, 30.4 tok/s, Runs well
198.1 GB required256.0 GB available
77% VRAM used

Fit status

Runs well

Decode

30.4 tok/s

TTFT

6363 ms

Safe context

49K

Memory

198.1 GB / 256.0 GB

Memory breakdown

Weights144.0 GB
KV Cache27.7 GB
Runtime0.9 GB
Headroom25.6 GB

See how fast it feels

See how fast it feelsK EXAONE 236B A23B on AMD Instinct MI325X 256GB
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: 30.4 tok/s decode · 6.4s TTFT (warm) · 76 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 well30.4 tok/s3471 ms49K
CodingCRuns well30.4 tok/s6363 ms49K
Agentic CodingCTight fit30.4 tok/s9256 ms49K
ReasoningCRuns well30.4 tok/s7520 ms49K
RAGCTight fit30.4 tok/s11569 ms49K

Inference speed

K EXAONE 236B A23B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for K EXAONE 236B A23B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~3 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / MacMemoryQuantSpeed (tok/s)Fits?
Mac Studio M3 Ultra 256GB
256 GBQ4_K_M3.4Heavy offload
NVIDIARTX 5090 32GB
32 GBQ4_K_M2.0Too big
NVIDIARTX 4090 24GB
24 GBQ4_K_M2.0Too big
NVIDIARTX 4080 Super 16GB
16 GBQ4_K_M2.0Too big
NVIDIARTX 3090 24GB
24 GBQ4_K_M2.0Too big
NVIDIARTX 4070 12GB
12 GBQ4_K_M2.0Too big
NVIDIARTX 3060 12GB
12 GBQ4_K_M2.0Too big
NVIDIARTX 4060 8GB
8 GBQ4_K_M2.0Too big
RX 7900 XTX 24GB
24 GBQ4_K_M2.0Too big
MacBook Pro M4 Max 128GB
128 GBQ4_K_M2.0Too big
Mac Studio M2 Ultra 128GB
128 GBQ4_K_M2.0Too big
Mac Studio M1 Ultra 128GB
128 GBQ4_K_M2.0Too big
MacBook Pro M4 Max 64GB
64 GBQ4_K_M2.0Too big
MacBook Pro M3 Max 64GB
64 GBQ4_K_M2.0Too big
MacBook Pro M1 Max 64GB
64 GBQ4_K_M2.0Too big
MacBook Pro M4 Pro 48GB
48 GBQ4_K_M2.0Too big
NVIDIA2× RTX 4090 24GB
48 GBQ4_K_M2.0Too big
NVIDIA2× RTX 3090 24GB
48 GBQ4_K_M2.0Too big
2× RX 7900 XTX 24GB
48 GBQ4_K_M2.0Too big
NVIDIA4× RTX 3060 12GB
48 GBQ4_K_M2.0Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How K EXAONE 236B A23B (236B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
92.0 GB
LowC44
Q3_K_S
3
115.6 GB
LowC46
NVFP4
4
132.2 GB
MediumC47
Q4_K_M
4
144.0 GB
MediumC48
Q5_K_M
5
169.9 GB
HighC48
Q6_KBest for your GPU
6
193.5 GB
HighC48
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

アップグレードオプション

K EXAONE 236B A23Bを快適に動かすハードウェア

AMD Instinct MI350X 288GBコスパ重視
288 GB VRAM (+32)8000 GB/s (+2000)
C
Raises estimated decode speed by about 34%.40.6 tok/sデコード

Raises estimated decode speed by about 34%.

〜$8,000 MSRP

Frequently asked questions

Can AMD Instinct MI325X 256GB run K EXAONE 236B A23B?

Yes, AMD Instinct MI325X 256GB can run K EXAONE 236B A23B with a C grade (Runs well). Expected decode speed: 30.4 tok/s.

How much VRAM does K EXAONE 236B A23B need?

K EXAONE 236B A23B (236B parameters) requires approximately 198.1 GB of memory with Q4_K_M quantization.

What is the best quantization for K EXAONE 236B A23B?

The recommended quantization for K EXAONE 236B A23B is Q4_K_M, which balances quality and memory efficiency.

What speed will K EXAONE 236B A23B run at on AMD Instinct MI325X 256GB?

On AMD Instinct MI325X 256GB, K EXAONE 236B A23B achieves approximately 30.4 tokens per second decode speed with a time-to-first-token of 6363ms using Q4_K_M quantization.

Can AMD Instinct MI325X 256GB run K EXAONE 236B A23B for coding?

For coding workloads, K EXAONE 236B A23B on AMD Instinct MI325X 256GB receives a C grade with 30.4 tok/s and 49K context.

What context window can K EXAONE 236B A23B use on AMD Instinct MI325X 256GB?

On AMD Instinct MI325X 256GB, K EXAONE 236B A23B can safely use up to 49K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for AMD Instinct MI325X 256GBSee all hardware for K EXAONE 236B A23B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-lgai-exaone--k-exaone-236b-a23b-gguf-on-instinct-mi325x-256gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: