PLLuM 12B Chat — Hardware Requirements & GPU Compatibility
Chat
PLLuM 12B Chat is a 12.2B-parameter open language model from CYFRAGOVPL. It supports a context window of up to 131,072 tokens. At BF16 it needs about 25.21 GB of VRAM — see which GPUs and Macs can run it below.
4.0K downloads
7 likesSpecifications
- Publisher
- CYFRAGOVPL
- Parameters
- 12.2B
- Architecture
- MistralForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2025-11-19
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does PLLuM 12B Chat Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 25.2 GB | 51.6 GB | 24.50 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run PLLuM 12B Chat?
BF16 · 25.2 GBPLLuM 12B Chat (BF16) requires 25.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 33+ GB is recommended. Using the full 131K context window can add up to 26.4 GB, bringing total usage to 51.6 GB. 1 GPU can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Decent
— Enough VRAM, may be tightWhich Devices Can Run PLLuM 12B Chat?
BF16 · 25.2 GB15 devices with unified memory can run PLLuM 12B Chat, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (36 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does PLLuM 12B Chat need?
PLLuM 12B Chat requires 25.2 GB of VRAM at BF16. Full 131K context adds up to 26.4 GB (51.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 12.2B × 16 bits ÷ 8 = 24.5 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 27.1 GB (at full 131K context)
VRAM usage by quantization
BF1625.2 GBBF16 + full context51.6 GB- Can I run PLLuM 12B Chat on a Mac?
PLLuM 12B Chat requires at least 25.2 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 PLLuM 12B Chat locally?
Yes — PLLuM 12B Chat can run locally on consumer hardware. At BF16 quantization it needs 25.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is PLLuM 12B Chat?
At BF16, PLLuM 12B Chat can reach ~116 tok/s on AMD Instinct MI300X. 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 ÷ 25.2 × 0.55 = ~116 tok/s
Estimated speed at BF16 (25.2 GB)
~116 tok/s~86 tok/s~72 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of PLLuM 12B Chat?
At BF16, the download is about 24.50 GB.
- Which GPUs can run PLLuM 12B Chat?
1 consumer GPU can run PLLuM 12B Chat at BF16 (25.2 GB). Top options include NVIDIA GeForce RTX 5090.
- Which devices can run PLLuM 12B Chat?
15 devices with unified memory can run PLLuM 12B Chat at BF16 (25.2 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.