Kimi Dev 72B GGUF — Hardware Requirements & GPU Compatibility
Code
95 downloads
6 likesSpecifications
- Publisher
- bullerwins
- Family
- Kimi
- Parameters
- 72B
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Kimi Dev 72B GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 158.4 GB | — | 144.00 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Kimi Dev 72B GGUF?
BF16 · 158.4 GBKimi Dev 72B GGUF (BF16) requires 158.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 206+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Kimi Dev 72B GGUF?
BF16 · 158.4 GB4 devices with unified memory can run Kimi Dev 72B GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Pro M2 Ultra (192 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Kimi Dev 72B GGUF need?
Kimi Dev 72B GGUF requires 158.4 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 72B × 16 bits ÷ 8 = 144 GB
KV Cache + Overhead ≈ 14.4 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF16158.4 GB- Can NVIDIA GeForce RTX 5090 run Kimi Dev 72B GGUF?
No — Kimi Dev 72B GGUF requires at least 158.4 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Kimi Dev 72B GGUF on a Mac?
Kimi Dev 72B GGUF requires at least 158.4 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 Kimi Dev 72B GGUF locally?
Yes — Kimi Dev 72B GGUF can run locally on consumer hardware. At BF16 quantization it needs 158.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Kimi Dev 72B GGUF?
At BF16, Kimi Dev 72B GGUF can reach ~18 tok/s on AMD Instinct MI300X. 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 ÷ 158.4 × 0.55 = ~18 tok/s
Estimated speed at BF16 (158.4 GB)
AMD Instinct MI300X~18 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Kimi Dev 72B GGUF?
At BF16, the download is about 144.00 GB.
- Which GPUs can run Kimi Dev 72B GGUF?
No single consumer GPU has enough VRAM to run Kimi Dev 72B GGUF at BF16 (158.4 GB). Multi-GPU or professional hardware is required.
- Which devices can run Kimi Dev 72B GGUF?
4 devices with unified memory can run Kimi Dev 72B GGUF at BF16 (158.4 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.