Grug 27B — Hardware Requirements & GPU Compatibility
ChatReasoningFunctions
Grug 27B is a 27.4B-parameter open language model from ProCreations. It supports a context window of up to 262,144 tokens. At BF16 it needs about 55.46 GB of VRAM — see which GPUs and Macs can run it below.
1.1K downloads
99 likesSpecifications
- Publisher
- ProCreations
- Parameters
- 27.4B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-07-23
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Grug 27B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 55.5 GB | 112.3 GB | 54.71 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 Grug 27B?
BF16 · 55.5 GBGrug 27B (BF16) requires 55.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 73+ GB is recommended. Using the full 262K context window can add up to 56.8 GB, bringing total usage to 112.3 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Grug 27B?
BF16 · 55.5 GB22 devices with unified memory can run Grug 27B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).
Runs great
— Plenty of headroom
Related Models
Frequently Asked Questions
- How much VRAM does Grug 27B need?
Grug 27B requires 55.5 GB of VRAM at BF16. Full 262K context adds up to 56.8 GB (112.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 27.4B × 16 bits ÷ 8 = 54.7 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 57.6 GB (at full 262K context)
VRAM usage by quantization
BF1655.5 GBBF16 + full context112.3 GB- Can NVIDIA GeForce RTX 5090 run Grug 27B?
No — Grug 27B requires at least 55.5 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Grug 27B on a Mac?
Grug 27B requires at least 55.5 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 Grug 27B locally?
Yes — Grug 27B can run locally on consumer hardware. At BF16 quantization it needs 55.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Grug 27B?
At BF16, Grug 27B can reach ~87 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 55.5 × 0.65 = ~94 tok/s
Estimated speed at BF16 (55.5 GB)
~94 tok/s~94 tok/s~87 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Grug 27B?
At BF16, the download is about 54.71 GB.
- Which GPUs can run Grug 27B?
No single consumer GPU has enough VRAM to run Grug 27B at BF16 (55.5 GB). Multi-GPU or professional hardware is required.
- Which devices can run Grug 27B?
23 devices with unified memory can run Grug 27B at BF16 (55.5 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.