Supergemma4 E4b Abliterated — Hardware Requirements & GPU Compatibility
Chat
Supergemma4 E4b Abliterated is a 7.5B-parameter open language model from Jiunsong in the Gemma family. It supports a context window of up to 131,072 tokens. At BF16 it needs about 15.56 GB of VRAM — see which GPUs and Macs can run it below.
1.8K downloads
70 likesSpecifications
- Publisher
- Jiunsong
- Family
- Gemma
- Parameters
- 7.5B
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-04-17
- License
- Gemma Terms
Get Started
HuggingFace
How Much VRAM Does Supergemma4 E4b Abliterated Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 15.6 GB | 29.4 GB | 15.04 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Supergemma4 E4b Abliterated?
BF16 · 15.6 GBSupergemma4 E4b Abliterated (BF16) requires 15.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 21+ GB is recommended. Using the full 131K context window can add up to 13.9 GB, bringing total usage to 29.4 GB. 17 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 Supergemma4 E4b Abliterated?
BF16 · 15.6 GB27 devices with unified memory can run Supergemma4 E4b Abliterated, 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 Supergemma4 E4b Abliterated need?
Supergemma4 E4b Abliterated requires 15.6 GB of VRAM at BF16. Full 131K context adds up to 13.9 GB (29.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 7.5B × 16 bits ÷ 8 = 15 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 14.4 GB (at full 131K context)
VRAM usage by quantization
BF1615.6 GBBF16 + full context29.4 GB- Can I run Supergemma4 E4b Abliterated on a Mac?
Supergemma4 E4b Abliterated requires at least 15.6 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 Supergemma4 E4b Abliterated locally?
Yes — Supergemma4 E4b Abliterated can run locally on consumer hardware. At BF16 quantization it needs 15.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Supergemma4 E4b Abliterated?
At BF16, Supergemma4 E4b Abliterated can reach ~187 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~42 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 ÷ 15.6 × 0.55 = ~187 tok/s
Estimated speed at BF16 (15.6 GB)
~187 tok/s~42 tok/s~140 tok/s~116 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Supergemma4 E4b Abliterated?
At BF16, the download is about 15.04 GB.
- Which GPUs can run Supergemma4 E4b Abliterated?
17 consumer GPUs can run Supergemma4 E4b Abliterated at BF16 (15.6 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 5 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Supergemma4 E4b Abliterated?
27 devices with unified memory can run Supergemma4 E4b Abliterated at BF16 (15.6 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.