Mamba 130M HF GGUF — Hardware Requirements & GPU Compatibility
Chat
57 downloads
1 likesSpecifications
- Publisher
- mradermacher
- Parameters
- 130M
Get Started
HuggingFace
How Much VRAM Does Mamba 130M HF GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 0.3 GB | — | 0.26 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Mamba 130M HF GGUF?
BF16 · 0.3 GBMamba 130M HF GGUF (BF16) requires 0.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Mamba 130M HF GGUF?
BF16 · 0.3 GB33 devices with unified memory can run Mamba 130M HF GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Mamba 130M HF GGUF need?
Mamba 130M HF GGUF requires 0.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 130M × 16 bits ÷ 8 = 0.3 GB
VRAM usage by quantization
BF160.3 GB- Can I run Mamba 130M HF GGUF on a Mac?
Mamba 130M HF GGUF requires at least 0.3 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 Mamba 130M HF GGUF locally?
Yes — Mamba 130M HF GGUF can run locally on consumer hardware. At BF16 quantization it needs 0.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Mamba 130M HF GGUF?
At BF16, Mamba 130M HF GGUF can reach ~10052 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~2259 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 ÷ 0.3 × 0.55 = ~10052 tok/s
Estimated speed at BF16 (0.3 GB)
AMD Instinct MI300X~10052 tok/sNVIDIA GeForce RTX 4090~2259 tok/sNVIDIA H100 SXM~7513 tok/sAMD Instinct MI250X~6215 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Mamba 130M HF GGUF?
At BF16, the download is about 0.26 GB.
- Which GPUs can run Mamba 130M HF GGUF?
35 consumer GPUs can run Mamba 130M HF GGUF at BF16 (0.3 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Mamba 130M HF GGUF?
33 devices with unified memory can run Mamba 130M HF GGUF at BF16 (0.3 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.