Plutus 8B Instruct — Hardware Requirements & GPU Compatibility
Chat
94 downloads
10 likesSpecifications
- Publisher
- TheFinAI
- Parameters
- 8.2B
- Architecture
- LlamaForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 149,248
- Release Date
- 2025-02-27
- License
- Llama 3.1 Community
Get Started
HuggingFace
How Much VRAM Does Plutus 8B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| FP16 | 16.00 | 17.0 GB | 33.9 GB | 16.40 GB | Full half-precision — baseline for inference |
Which GPUs Can Run Plutus 8B Instruct?
FP16 · 17.0 GBPlutus 8B Instruct (FP16) requires 17.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 23+ GB is recommended. Using the full 131K context window can add up to 16.9 GB, bringing total usage to 33.9 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 Plutus 8B Instruct?
FP16 · 17.0 GB21 devices with unified memory can run Plutus 8B Instruct, 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 Plutus 8B Instruct need?
Plutus 8B Instruct requires 17.0 GB of VRAM at FP16. Full 131K context adds up to 16.9 GB (33.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.2B × 16 bits ÷ 8 = 16.4 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 17.5 GB (at full 131K context)
VRAM usage by quantization
FP1617.0 GBFP16 + full context33.9 GB- Can I run Plutus 8B Instruct on a Mac?
Plutus 8B Instruct requires at least 17.0 GB at FP16, 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 Plutus 8B Instruct locally?
Yes — Plutus 8B Instruct can run locally on consumer hardware. At FP16 quantization it needs 17.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Plutus 8B Instruct?
At FP16, Plutus 8B Instruct can reach ~172 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~39 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 ÷ 17.0 × 0.55 = ~172 tok/s
Estimated speed at FP16 (17.0 GB)
AMD Instinct MI300X~172 tok/sNVIDIA GeForce RTX 4090~39 tok/sNVIDIA H100 SXM~128 tok/sAMD Instinct MI250X~106 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Plutus 8B Instruct?
At FP16, the download is about 16.40 GB.
- Which GPUs can run Plutus 8B Instruct?
6 consumer GPUs can run Plutus 8B Instruct at FP16 (17.0 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 Plutus 8B Instruct?
21 devices with unified memory can run Plutus 8B Instruct at FP16 (17.0 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.