Mamba 130M HF — Hardware Requirements & GPU Compatibility
Chat
Mamba 130M is a state-space model developed by State Spaces that offers a fundamentally different architecture from the Transformer-based models that dominate the LLM landscape. Using selective state-space layers instead of attention, Mamba achieves linear-time inference scaling with sequence length, making it particularly efficient for processing long inputs. At 130 million parameters this is primarily a research and demonstration model, but it showcases the potential of state-space architectures for local deployment. Users interested in exploring alternatives to Transformer-based language models will find Mamba 130M a lightweight and accessible entry point for experimentation.
179.2K downloads
69 likesSpecifications
- Publisher
- State Spaces
- Parameters
- 129M
- Architecture
- MambaForCausalLM
- Vocabulary Size
- 50,280
- Release Date
- 2024-03-06
Get Started
HuggingFace
How Much VRAM Does Mamba 130M HF 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?
BF16 · 0.3 GBMamba 130M HF (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?
BF16 · 0.3 GB33 devices with unified memory can run Mamba 130M HF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Derivatives (1)
Frequently Asked Questions
- How much VRAM does Mamba 130M HF need?
Mamba 130M HF requires 0.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 129M × 16 bits ÷ 8 = 0.3 GB
VRAM usage by quantization
BF160.3 GB- Can I run Mamba 130M HF on a Mac?
Mamba 130M HF 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 locally?
Yes — Mamba 130M HF 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?
At BF16, Mamba 130M HF can reach ~10411 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~2340 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 = ~10411 tok/s
Estimated speed at BF16 (0.3 GB)
~10411 tok/s~2340 tok/s~7781 tok/s~6437 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?
At BF16, the download is about 0.26 GB.
- Which GPUs can run Mamba 130M HF?
35 consumer GPUs can run Mamba 130M HF 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?
33 devices with unified memory can run Mamba 130M HF 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.