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 Q4_K_M it needs about 8.07 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
- 2025-02-07
- 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 |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 5.9 GB | 32.4 GB | 5.21 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 6.7 GB | 33.1 GB | 5.97 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 8.1 GB | 34.5 GB | 7.35 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 9.4 GB | 35.9 GB | 8.73 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 10.8 GB | 37.3 GB | 10.10 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 13.0 GB | 39.4 GB | 12.25 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 25.2 GB | 51.6 GB | 24.50 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run PLLuM 12B Chat?
Q4_K_M · 8.1 GBPLLuM 12B Chat (Q4_K_M) requires 8.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 11+ GB is recommended. Using the full 131K context window can add up to 26.4 GB, bringing total usage to 34.5 GB. 39 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run PLLuM 12B Chat?
Q4_K_M · 8.1 GB49 devices with unified memory can run PLLuM 12B Chat, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 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 8.1 GB of VRAM at Q4_K_M, or 25.2 GB at BF16. Full 131K context adds up to 26.4 GB (34.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 12.2B × 4.8 bits ÷ 8 = 7.3 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 27.2 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M8.1 GBQ4_K_M + full context34.5 GB- Can NVIDIA GeForce RTX 4090 run PLLuM 12B Chat?
Yes, at Q8_0 (13.0 GB) or lower. Higher quantizations like BF16 (25.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for PLLuM 12B Chat?
For PLLuM 12B Chat, Q4_K_M (8.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (9.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 5.9 GB.
VRAM requirement by quantization
Q2_K5.9 GBQ4_K_M ★8.1 GBQ5_K_M9.4 GBQ6_K10.8 GBQ8_013.0 GBBF1625.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run PLLuM 12B Chat on a Mac?
PLLuM 12B Chat requires at least 5.9 GB at Q2_K, 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 Q4_K_M quantization it needs 8.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is PLLuM 12B Chat?
At Q4_K_M, PLLuM 12B Chat can reach ~545 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~81 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 ÷ 8.1 × 0.65 = ~644 tok/s
Estimated speed at Q4_K_M (8.1 GB)
~644 tok/s~81 tok/s~644 tok/s~545 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 Q4_K_M, the download is about 7.35 GB. The full-precision BF16 version is 24.50 GB. The smallest option (Q2_K) is 5.21 GB.
- Which GPUs can run PLLuM 12B Chat?
39 consumer GPUs can run PLLuM 12B Chat at Q4_K_M (8.1 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
- Which devices can run PLLuM 12B Chat?
52 devices with unified memory can run PLLuM 12B Chat at Q4_K_M (8.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.