GPT J 6B Dolly GGUF — Hardware Requirements & GPU Compatibility
Chat
GPT J 6B Dolly GGUF is a 6B-parameter open language model from Corianas. At BF16 it needs about 13.20 GB of VRAM — see which GPUs and Macs can run it below.
Specifications
- Publisher
- Corianas
- Parameters
- 6B
- License
- cc-by-sa-3.0
Get Started
HuggingFace
How Much VRAM Does GPT J 6B Dolly GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 13.2 GB | — | 12.00 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run GPT J 6B Dolly GGUF?
BF16 · 13.2 GBGPT J 6B Dolly GGUF (BF16) requires 13.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 18+ GB is recommended. 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 GPT J 6B Dolly GGUF?
BF16 · 13.2 GB27 devices with unified memory can run GPT J 6B Dolly 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 GPT J 6B Dolly GGUF need?
GPT J 6B Dolly GGUF requires 13.2 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 6B × 16 bits ÷ 8 = 12 GB
KV Cache + Overhead ≈ 1.2 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF1613.2 GB- Can I run GPT J 6B Dolly GGUF on a Mac?
GPT J 6B Dolly GGUF requires at least 13.2 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 GPT J 6B Dolly GGUF locally?
Yes — GPT J 6B Dolly GGUF can run locally on consumer hardware. At BF16 quantization it needs 13.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GPT J 6B Dolly GGUF?
At BF16, GPT J 6B Dolly GGUF can reach ~221 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~50 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 ÷ 13.2 × 0.55 = ~221 tok/s
Estimated speed at BF16 (13.2 GB)
~221 tok/s~50 tok/s~165 tok/s~137 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GPT J 6B Dolly GGUF?
At BF16, the download is about 12.00 GB.
- Which GPUs can run GPT J 6B Dolly GGUF?
17 consumer GPUs can run GPT J 6B Dolly GGUF at BF16 (13.2 GB). Top options include AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, AMD Radeon RX 6800. 6 GPUs have plenty of headroom for comfortable inference.
- Which devices can run GPT J 6B Dolly GGUF?
27 devices with unified memory can run GPT J 6B Dolly GGUF at BF16 (13.2 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.