llmrun
Shrijanagain

SKT OMNI SUPREME — Hardware Requirements & GPU Compatibility

ChatFunctions

SKT OMNI SUPREME is a 170.7B-parameter open language model from Shrijanagain. At BF16 it needs about 375.62 GB of VRAM — see which GPUs and Macs can run it below.

170.7B params · densecreativeml-openrail-m962 downloads5 likes

SKT OMNI SUPREME runs on a 512 GB+ Mac or a multi-GPU server

Best local pick → Mac Studio (M3 Ultra, 512GB) · BF16 · 381.7 GB · ~2 tok/s

Macs from512 GB BF16 · ~2 tok/s

creativeml-openrail-m

Not set up for it?

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run SKT OMNI SUPREME

One recommended way. Every other method, OS and quant is in the step-by-step guide.

Recommended

vLLM on a multi-GPU server
tensor + pipeline parallel · needs vLLM on every node
$vllm serve Shrijanagain/SKT_OMNI_SUPREME --max-model-len 16384 --tensor-parallel-size 8

Size the nodes from the table above

Download: Weights on Hugging Face

install, other ways

Other ways

each opens step-by-step

Run in cloud

Rent 6× H100 SXM · BF16

Estimated hourly price
~$13.27/hr
est., whole server
GPUs
6 GPUs
480 GB of VRAM

How Much VRAM Does SKT OMNI SUPREME Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KRuns on
375.6 GB388.6 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingRuns on 6× H100 SXM 80 GB
est.calculated, no published file yet

Selected BF16

Brain floating point 16

381.7GBat 16K context

Weights
374.5 GB
KV cache
6.9 GB
Overhead
0.3 GB

Server-class: ~381.7 GB at 16K context · about 6× H100 SXM 80 GB

Which Hardware Can Run SKT OMNI SUPREME?

BF16 · 375.6 GB

SKT OMNI SUPREME (BF16) requires 375.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 489+ GB is recommended. No consumer GPU has enough memory. 1 device with unified memory can run SKT OMNI SUPREME, including Mac Studio (M3 Ultra, 512GB).

Needs server-class hardware

SKT OMNI SUPREME runs on a 512 GB+ Mac or a multi-GPU server · BF16 needs ~381.7 GB

Hardware that runs this model
HardwareQuantMemorySpeedContextHardware page
Mac 512 GB · Mac Studio (M3 Ultra, 512GB)BF16381.7 GB~2 tok/s32K ctxMac Studio →BF16 · 381.7 GB · ~2 tok/s · 32K ctx
6× H100 SXM 80 GB · 480 GBBF16381.7 GB—32K ctxH100 SXM →BF16 · 381.7 GB · 32K ctx
4× H200 SXM 141 GB · 564 GBBF16381.7 GB—32K ctxH200 SXM →BF16 · 381.7 GB · 32K ctx
3× B200 192 GB · 576 GBBF16381.7 GB—32K ctxB200 →BF16 · 381.7 GB · 32K ctx

Also: Mac Studio (M3 Ultra, 512GB) · NVIDIA DGX A100 640GB · NVIDIA DGX H100

≤ 640 GB tier →

By VRAM tier · typical GPUs and Macs at BF16

Consumer GPUs (up to 32 GB) and Macs up to 256 GB: too small for this model (needs ≥ 381.7 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →

Alternatives to SKT OMNI SUPREME

Similar models

2
ModelScoreVRAMWhy it is similar
Qwen3.8 Flash NextAlibaba—109 GBsame size
DeepSeek V4 Flash DSparkDeepSeek—99.6 GBsame size
Fine-tunes & variants(1)

Specifications

Publisher
Shrijanagain
Parameters
170.7B
Release Date
2026-03-11
License
creativeml-openrail-m

Frequently Asked Questions

How much VRAM does SKT OMNI SUPREME need?

SKT OMNI SUPREME requires 375.6 GB of VRAM at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 170.7B × 16 bits ÷ 8 = 341.5 GB

KV Cache + Overhead ≈ 34.1 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

VRAM usage by quantization

375.6 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 5090 run SKT OMNI SUPREME?

No — SKT OMNI SUPREME requires at least 375.6 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

Can I run SKT OMNI SUPREME on a Mac?

Yes — Mac Studio (M3 Ultra, 512GB) and above can run SKT OMNI SUPREME. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 375.6 GB of usable unified memory (RAM minus macOS overhead).

Can I run SKT OMNI SUPREME locally?

Yes — SKT OMNI SUPREME can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

What's the download size of SKT OMNI SUPREME?

At BF16, the download is about 341.48 GB.

Which GPUs can run SKT OMNI SUPREME?

No single consumer GPU has enough VRAM to run SKT OMNI SUPREME at BF16 (375.6 GB). Multi-GPU or professional hardware is required.

Which devices can run SKT OMNI SUPREME?

1 device with unified memory can run SKT OMNI SUPREME at BF16 (375.6 GB), including Mac Studio (M3 Ultra, 512GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.