EXAONE 3.0 7.8B Instruct — Hardware Requirements & GPU Compatibility
Chat
EXAONE 3.0 7.8B Instruct is a 7.8B-parameter open language model from LGAI-EXAONE in the EXAONE family. At BF16 it needs about 17.20 GB of VRAM — see which GPUs and Macs can run it below.
41.7K downloads
420 likesSpecifications
- Publisher
- LGAI-EXAONE
- Family
- EXAONE
- Parameters
- 7.8B
- Release Date
- 2024-07-31
- License
- Other
Get Started
HuggingFace
How Much VRAM Does EXAONE 3.0 7.8B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 17.2 GB | — | 15.64 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run EXAONE 3.0 7.8B Instruct?
BF16 · 17.2 GBEXAONE 3.0 7.8B Instruct (BF16) requires 17.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 23+ GB is recommended. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run EXAONE 3.0 7.8B Instruct?
BF16 · 17.2 GB21 devices with unified memory can run EXAONE 3.0 7.8B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does EXAONE 3.0 7.8B Instruct need?
EXAONE 3.0 7.8B Instruct requires 17.2 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 7.8B × 16 bits ÷ 8 = 15.6 GB
KV Cache + Overhead ≈ 1.6 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF1617.2 GB- Can I run EXAONE 3.0 7.8B Instruct on a Mac?
EXAONE 3.0 7.8B Instruct requires at least 17.2 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 EXAONE 3.0 7.8B Instruct locally?
Yes — EXAONE 3.0 7.8B Instruct can run locally on consumer hardware. At BF16 quantization it needs 17.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is EXAONE 3.0 7.8B Instruct?
At BF16, EXAONE 3.0 7.8B Instruct can reach ~170 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~38 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 ÷ 17.2 × 0.55 = ~170 tok/s
Estimated speed at BF16 (17.2 GB)
~170 tok/s~38 tok/s~127 tok/s~105 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of EXAONE 3.0 7.8B Instruct?
At BF16, the download is about 15.64 GB.
- Which GPUs can run EXAONE 3.0 7.8B Instruct?
6 consumer GPUs can run EXAONE 3.0 7.8B Instruct at BF16 (17.2 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run EXAONE 3.0 7.8B Instruct?
21 devices with unified memory can run EXAONE 3.0 7.8B Instruct at BF16 (17.2 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.