SKT ST X 0 3B — Hardware Requirements & GPU Compatibility
Chat
SKT ST X 0 3B is a 3.4B-parameter open language model from sKT-Ai-Labs. It supports a context window of up to 2,048 tokens. At BF16 it needs about 7.11 GB of VRAM — see which GPUs and Macs can run it below.
639 downloads
4 likesSpecifications
- Publisher
- sKT-Ai-Labs
- Parameters
- 3.4B
- Architecture
- MixtralForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2026-06-04
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does SKT ST X 0 3B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 7.1 GB | — | 6.77 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run SKT ST X 0 3B?
BF16 · 7.1 GBSKT ST X 0 3B (BF16) requires 7.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 10+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080.
Runs great
— Plenty of headroom
Which Devices Can Run SKT ST X 0 3B?
BF16 · 7.1 GB33 devices with unified memory can run SKT ST X 0 3B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does SKT ST X 0 3B need?
SKT ST X 0 3B requires 7.1 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 3.4B × 16 bits ÷ 8 = 6.8 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF167.1 GB- Can I run SKT ST X 0 3B on a Mac?
SKT ST X 0 3B requires at least 7.1 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run SKT ST X 0 3B locally?
Yes — SKT ST X 0 3B can run locally on consumer hardware. At BF16 quantization it needs 7.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is SKT ST X 0 3B?
At BF16, SKT ST X 0 3B can reach ~410 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~92 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 7.1 × 0.55 = ~410 tok/s
Estimated speed at BF16 (7.1 GB)
~410 tok/s~92 tok/s~306 tok/s~254 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of SKT ST X 0 3B?
At BF16, the download is about 6.77 GB.
- Which GPUs can run SKT ST X 0 3B?
35 consumer GPUs can run SKT ST X 0 3B at BF16 (7.1 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 27 GPUs have plenty of headroom for comfortable inference.
- Which devices can run SKT ST X 0 3B?
33 devices with unified memory can run SKT ST X 0 3B at BF16 (7.1 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.