Supergemma4 E4b Abliterated — Hardware Requirements & GPU Compatibility
Chat
Supergemma4 E4b Abliterated is a 7.5B-parameter open language model from Jiunsong in the Gemma 4 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 5.03 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 128K)Best on 24 GB (Q4_K_M · ~130 tok/s · 128K)Macs from 8 GB (Q3_K_M · ~17 tok/s)
Gemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Supergemma4 E4b Abliterated
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Jiunsong/supergemma4-e4b-abliterated --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (6 GB headroom) · Q4_K_M
- Generation speed
- ~47 tok/s
- generation speed
- Cost per 1M output tokens
- $0.50
- per 1M output tokens
How Much VRAM Does Supergemma4 E4b Abliterated Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.7 GB | 4.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~176 tok/s | |
| 4.2 GB | 4.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~156 tok/s | |
| 5.0 GB | 5.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~130 tok/s | |
| 5.9 GB | 6.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~111 tok/s | |
| 6.7 GB | 7.3 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~98 tok/s | |
| 8.0 GB | 8.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~82 tok/s | |
| 15.6 GB | 16.2 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~42 tok/s |
Selected Q4_K_M
4-bit medium quantization5.3GBat 16K context
- Weights
- 4.5 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 18.7 GB free · ~130 tok/s
≥50 tok/s needs ≥387 GB/s · RTX 5090 ~232, RTX 3090 Ti ~130
Which Hardware Can Run Supergemma4 E4b Abliterated?
Q4_K_M · 5.0 GBSupergemma4 E4b Abliterated (Q4_K_M) requires 5.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 131K context window can add up to 2.9 GB, bringing total usage to 7.9 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run Supergemma4 E4b Abliterated, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 2.7 GB free · up to 128K ctx
16 GPUs · 1 device family
RTX 3080~98Simulate output on RTX 3080RTX 2080 Ti~80Simulate output on RTX 2080 TiRTX 3070 Ti~79Simulate output on RTX 3070 TiOrin Nano~13Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 14.7 GB free · up to 128K ctx
1 GPU
RX 7900 XT~95Simulate output on RX 7900 XT32–40 GB
fits · 26.7 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~232Simulate output on RTX 5090M5 Max36 GB~64Simulate output on Mac Studio M5 Max (36 GB)M532 GB~21Simulate output on MacBook Air 13" M5 (32 GB)Orin~27Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~17Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Supergemma4 E4b Abliterated
Gemma 4 family · 35 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
| Olmo 3 7B InstructAllen AI | — | 8.4 GB | ~114 | same size |
| Phi Mini MoE InstructMicrosoft | — | 5.4 GB | ~239 | same size |
| Gemma 3n E4B ITGoogle | — | 7.7 GB | ~127 | same size |
| Falcon H1 7B InstructTII UAE | — | 6.3 GB | ~130 | same size |
Specifications
- Publisher
- Jiunsong
- Family
- Gemma 4
- Parameters
- 7.5B
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-04-17
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Supergemma4 E4b Abliterated need?
Supergemma4 E4b Abliterated requires 5.0 GB of VRAM at Q4_K_M, or 15.6 GB at BF16. Full 131K context adds up to 2.9 GB (7.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 7.5B × 4.8 bits ÷ 8 = 4.5 GB
KV Cache + Overhead ≈ 0.5 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.
KV Cache + Overhead ≈ 3.4 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Supergemma4 E4b Abliterated?
For Supergemma4 E4b Abliterated, Q4_K_M (5.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (5.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Supergemma4 E4b Abliterated on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Supergemma4 E4b Abliterated, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.0 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run Supergemma4 E4b Abliterated locally?
Yes — Supergemma4 E4b Abliterated can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Supergemma4 E4b Abliterated?
At Q4_K_M, Supergemma4 E4b Abliterated can reach ~954 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~130 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 ÷ 5.03 × 0.65 = ~1034 tok/s
Estimated speed at Q4_K_M (5.0 GB)
Real-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 Q4_K_M, the download is about 4.51 GB. The full-precision BF16 version is 15.04 GB. The smallest option (Q2_K) is 3.20 GB.
Which GPUs can run Supergemma4 E4b Abliterated?
52 consumer GPUs can run Supergemma4 E4b Abliterated at Q4_K_M. 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 Supergemma4 E4b Abliterated?
151 devices with unified memory can run Supergemma4 E4b Abliterated at Q4_K_M (5.0 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.