Adelic Gemma 4 12B GGUF — Hardware Requirements & GPU Compatibility
Chat
Adelic Gemma 4 12B GGUF is a 12B-parameter open language model from sneedjak in the Gemma family. At Q6_K it needs about 10.89 GB of VRAM — see which GPUs and Macs can run it below.
16.1K downloads
2 likesSpecifications
- Publisher
- sneedjak
- Family
- Gemma
- Parameters
- 12B
- Release Date
- 2026-06-05
- License
- Gemma Terms
Get Started
HuggingFace
How Much VRAM Does Adelic Gemma 4 12B GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q6_K | 6.60 | 10.9 GB | — | 9.90 GB | 6-bit quantization, very good quality |
Which GPUs Can Run Adelic Gemma 4 12B GGUF?
Q6_K · 10.9 GBAdelic Gemma 4 12B GGUF (Q6_K) requires 10.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 15+ GB is recommended. 27 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Adelic Gemma 4 12B GGUF?
Q6_K · 10.9 GB27 devices with unified memory can run Adelic Gemma 4 12B GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Adelic Gemma 4 12B GGUF need?
Adelic Gemma 4 12B GGUF requires 10.9 GB of VRAM at Q6_K.
VRAM = Weights + KV Cache + Overhead
Weights = 12B × 6.6 bits ÷ 8 = 9.9 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q6_K10.9 GB- Can I run Adelic Gemma 4 12B GGUF on a Mac?
Adelic Gemma 4 12B GGUF requires at least 10.9 GB at Q6_K, 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 Adelic Gemma 4 12B GGUF locally?
Yes — Adelic Gemma 4 12B GGUF can run locally on consumer hardware. At Q6_K quantization it needs 10.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Adelic Gemma 4 12B GGUF?
At Q6_K, Adelic Gemma 4 12B GGUF can reach ~268 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~60 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 ÷ 10.9 × 0.55 = ~268 tok/s
Estimated speed at Q6_K (10.9 GB)
~268 tok/s~60 tok/s~200 tok/s~166 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Adelic Gemma 4 12B GGUF?
At Q6_K, the download is about 9.90 GB.
- Which GPUs can run Adelic Gemma 4 12B GGUF?
27 consumer GPUs can run Adelic Gemma 4 12B GGUF at Q6_K (10.9 GB). Top options include AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, AMD Radeon RX 6700 XT. 6 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Adelic Gemma 4 12B GGUF?
27 devices with unified memory can run Adelic Gemma 4 12B GGUF at Q6_K (10.9 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.