Nandi Mini 150M — Hardware Requirements & GPU Compatibility
Chat
Nandi Mini 150M is a 153M-parameter open language model from FrontiersMind. It supports a context window of up to 2,048 tokens. At BF16 it needs about 0.63 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 2K)Best on 24 GB (BF16 · ~1040 tok/s · 2K)Macs from 8 GB (BF16 · ~114 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Nandi Mini 150M
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve FrontiersMind/Nandi-Mini-150M --max-model-len 2048vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (11 GB headroom) · BF16
- Generation speed
- ~371 tok/s
- generation speed
- Cost per 1M output tokens
- $0.062
- per 1M output tokens
How Much VRAM Does Nandi Mini 150M Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.6 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 2K context · ~1040 tok/s |
Selected BF16
Brain floating point 160.6GBat 2K context
- Weights
- 0.3 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.4 GB free · ~1040 tok/s
≥50 tok/s needs ≥48 GB/s · RTX 5090 ~1849, RTX 3090 Ti ~1040
Which Hardware Can Run Nandi Mini 150M?
BF16 · 0.6 GBNandi Mini 150M (BF16) requires 0.6 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 Nandi Mini 150M, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.4 GB free · up to 2K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~784Simulate output on RTX 3080RTX 2080 Ti~636Simulate output on RTX 2080 TiRTX 3070 Ti~628Simulate output on RTX 3070 TiM3*8 GB~114Simulate output on iMac 24" M3 (8 GB)Orin Nano~105Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~76Simulate output on iPhone 1720 GB
fits · 19.4 GB free · up to 2K ctx
1 GPU
RX 7900 XT~762Simulate output on RX 7900 XT32–40 GB
fits · 31.4 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1849Simulate output on RTX 5090M5 Max36 GB~511Simulate output on Mac Studio M5 Max (36 GB)M532 GB~171Simulate output on MacBook Air 13" M5 (32 GB)Orin~211Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~139Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llama 160MJackFram | — | 0.5 GB | ~1394 | same size |
Specifications
- Publisher
- FrontiersMind
- Parameters
- 153M
- Architecture
- NandiForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-04-01
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Nandi Mini 150M need?
Nandi Mini 150M requires 0.6 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 153M × 16 bits ÷ 8 = 0.3 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
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
Can I run Nandi Mini 150M on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Nandi Mini 150M. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Nandi Mini 150M locally?
Yes — Nandi Mini 150M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Nandi Mini 150M?
At BF16, Nandi Mini 150M can reach ~7619 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1040 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 ÷ 0.63 × 0.65 = ~8254 tok/s
Estimated speed at BF16 (0.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Nandi Mini 150M?
At BF16, the download is about 0.31 GB.
Which GPUs can run Nandi Mini 150M?
52 consumer GPUs can run Nandi Mini 150M at BF16. 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 Nandi Mini 150M?
163 devices with unified memory can run Nandi Mini 150M at BF16 (0.6 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.