Gemma4 E4B MiniFantasy V1 — Hardware Requirements & GPU Compatibility
ChatRoleplay
Gemma4 E4B MiniFantasy V1 is a 8.0B-parameter open language model from Nubinu in the Gemma family. It supports a context window of up to 131,072 tokens. At BF16 it needs about 16.51 GB of VRAM — see which GPUs and Macs can run it below.
344 downloads
4 likesSpecifications
- Publisher
- Nubinu
- Family
- Gemma
- Parameters
- 8.0B
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-06-03
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Gemma4 E4B MiniFantasy V1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 16.5 GB | 30.4 GB | 15.99 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Gemma4 E4B MiniFantasy V1?
BF16 · 16.5 GBGemma4 E4B MiniFantasy V1 (BF16) requires 16.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 22+ GB is recommended. Using the full 131K context window can add up to 13.9 GB, bringing total usage to 30.4 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Gemma4 E4B MiniFantasy V1?
BF16 · 16.5 GB21 devices with unified memory can run Gemma4 E4B MiniFantasy V1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Gemma4 E4B MiniFantasy V1 need?
Gemma4 E4B MiniFantasy V1 requires 16.5 GB of VRAM at BF16. Full 131K context adds up to 13.9 GB (30.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.0B × 16 bits ÷ 8 = 16 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 14.4 GB (at full 131K context)
VRAM usage by quantization
BF1616.5 GBBF16 + full context30.4 GB- Can I run Gemma4 E4B MiniFantasy V1 on a Mac?
Gemma4 E4B MiniFantasy V1 requires at least 16.5 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 Gemma4 E4B MiniFantasy V1 locally?
Yes — Gemma4 E4B MiniFantasy V1 can run locally on consumer hardware. At BF16 quantization it needs 16.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Gemma4 E4B MiniFantasy V1?
At BF16, Gemma4 E4B MiniFantasy V1 can reach ~177 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~40 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 ÷ 16.5 × 0.55 = ~177 tok/s
Estimated speed at BF16 (16.5 GB)
~177 tok/s~40 tok/s~132 tok/s~109 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Gemma4 E4B MiniFantasy V1?
At BF16, the download is about 15.99 GB.
- Which GPUs can run Gemma4 E4B MiniFantasy V1?
6 consumer GPUs can run Gemma4 E4B MiniFantasy V1 at BF16 (16.5 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Gemma4 E4B MiniFantasy V1?
21 devices with unified memory can run Gemma4 E4B MiniFantasy V1 at BF16 (16.5 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.