Nanowhale 100M — Hardware Requirements & GPU Compatibility
Chat
Nanowhale 100M is a 110M-parameter open language model from cmpatino. It supports a context window of up to 2,048 tokens. At BF16 it needs about 0.52 GB of VRAM — see which GPUs and Macs can run it below.
629 downloads
20 likesSpecifications
- Publisher
- cmpatino
- Parameters
- 110M
- Architecture
- DeepseekV4ForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2026-05-04
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Nanowhale 100M Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 0.5 GB | — | 0.22 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Nanowhale 100M?
BF16 · 0.5 GBNanowhale 100M (BF16) requires 0.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Nanowhale 100M?
BF16 · 0.5 GB59 devices with unified memory can run Nanowhale 100M, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Nanowhale 100M need?
Nanowhale 100M requires 0.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 110M × 16 bits ÷ 8 = 0.2 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF160.5 GB- Can I run Nanowhale 100M on a Mac?
Nanowhale 100M requires at least 0.5 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 Nanowhale 100M locally?
Yes — Nanowhale 100M can run locally on consumer hardware. At BF16 quantization it needs 0.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Nanowhale 100M?
At BF16, Nanowhale 100M can reach ~8462 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1260 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 ÷ 0.5 × 0.65 = ~10000 tok/s
Estimated speed at BF16 (0.5 GB)
~10000 tok/s~1260 tok/s~10000 tok/s~8462 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Nanowhale 100M?
At BF16, the download is about 0.22 GB.
- Which GPUs can run Nanowhale 100M?
50 consumer GPUs can run Nanowhale 100M at BF16 (0.5 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Nanowhale 100M?
59 devices with unified memory can run Nanowhale 100M at BF16 (0.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.