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.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~7280 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~796 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Mamba 130M HF
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/mamba-130m-hf-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 23.1 GB free · 16K context
Download: mamba-130m-hf.Q4_K_M.gguf0.09 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3080 Ti (12 GB) (11 GB headroom) · Q4_K_M
- Generation speed
- ~6590 tok/s
- generation speed
- Cost per 1M output tokens
- $0.0052
- per 1M output tokens
How Much VRAM Does Mamba 130M HF Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.1 GB | 1.8 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~10920 tok/s | |
| 0.1 GB | 1.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~10920 tok/s | |
| 0.1 GB | 1.8 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~9360 tok/s | |
| 0.1 GB | 1.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~9360 tok/s | |
| 0.1 GB | 1.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~7280 tok/s | |
| 0.1 GB | 1.8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~6552 tok/s | |
| 0.1 GB | 1.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~5460 tok/s | |
| 0.1 GB | 1.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~4680 tok/s |
Selected Q4_K_M
4-bit medium quantization0.9GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.1 GB free · ~7280 tok/s
≥50 tok/s needs ≥7 GB/s · RTX 5090 ~12942, RTX 3090 Ti ~7280
Which Hardware Can Run Mamba 130M HF?
Q4_K_M · 0.1 GBMamba 130M HF (Q4_K_M) requires 0.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Mamba 130M HF, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.1 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~5491Simulate output on RTX 3080RTX 2080 Ti~4449Simulate output on RTX 2080 TiRTX 3070 Ti~4393Simulate output on RTX 3070 TiM3*8 GB~796Simulate output on iMac 24" M3 (8 GB)Orin Nano~737Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~530Simulate output on iPhone 1720 GB
fits · 19.1 GB free · up to 32K ctx
1 GPU
RX 7900 XT~5333Simulate output on RX 7900 XT32–40 GB
fits · 31.1 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~12942Simulate output on RTX 5090M5 Max36 GB~3578Simulate output on Mac Studio M5 Max (36 GB)M532 GB~1195Simulate output on MacBook Air 13" M5 (32 GB)Orin~1479Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~975Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| SmolLM 135M Instruct FP32modularai | — | 0.4 GB | ~1524 | same size |
Specifications
- Publisher
- State Spaces
- Parameters
- 129M
- Architecture
- MambaForCausalLM
- Vocabulary Size
- 50,280
- Release Date
- 2024-03-06
Frequently Asked Questions
How much VRAM does Mamba 130M HF need?
Mamba 130M HF requires 0.1 GB of VRAM at Q4_K_M, or 0.3 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 129M × 4.8 bits ÷ 8 = 0.1 GB
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
What's the best quantization for Mamba 130M HF?
For Mamba 130M HF, Q4_K_M (0.1 GB) offers the best balance of quality and VRAM usage. Q5_K_S (0.1 GB) provides better quality if you have the VRAM. The smallest option is IQ3_M at 0.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Mamba 130M HF on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Mamba 130M HF. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Mamba 130M HF locally?
Yes — Mamba 130M HF can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Mamba 130M HF?
At Q4_K_M, Mamba 130M HF can reach ~53333 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~7280 tok/s. 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 ÷ 0.09 × 0.65 = ~57778 tok/s
Estimated speed at Q4_K_M (0.1 GB)
Real-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 Q4_K_M, the download is about 0.08 GB. The full-precision BF16 version is 0.26 GB. The smallest option (IQ3_M) is 0.06 GB.
Which GPUs can run Mamba 130M HF?
52 consumer GPUs can run Mamba 130M HF at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Mamba 130M HF?
163 devices with unified memory can run Mamba 130M HF at Q4_K_M (0.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, 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.