Roleplaiapp Q4_K_M 115B Parameters

VRAM Requirements for
Llama-3-monika-ddlc-11.5b-v1-i1-Q4_K_M-GGUF Q4_K_M

To run Llama-3-monika-ddlc-11.5b-v1-i1-Q4_K_M-GGUF locally at Q4_K_M quantization, you need at minimum 68.57 GB of GPU VRAM.

68.57 GB
Required VRAM
64.69 GB
File Size
8K tokens
Context Window
115B
Parameters
Estimated VRAM Required
68.57
GB
Data Centre Class
0 16GB
RTX 3080 48GB
A6000 80GB+

Recommended GPU Configurations

⚠️ 20.6 GB short
Budget $3,200 – $4,000

2× RTX 4090 (48GB) + aggressive quant

48 GB

Use a lower quantization to fit. Viable for testing at this scale.

Balanced $15,000 – $22,000

NVIDIA A100 80GB PCIe

80 GB HBM2e

Single-card 80GB. Industry-standard for large model inference.

Ultimate $25,000 – $40,000

NVIDIA H100 80GB SXM5

80 GB HBM3

State-of-the-art inference. 3× the bandwidth of A100.

📊 VRAM Calculation Breakdown

Model File Size (Q4_K_M) 64.69 GB
Context Overhead (8,192 tokens × 115B × 2 ÷ 1M) 1.884 GB
System Buffer (OS + CUDA runtime) 2.00 GB
Total Required VRAM 68.57 GB

Try a Different Quantization

Use the interactive calculator to compare Llama-3-monika-ddlc-11.5b-v1-i1-Q4_K_M-GGUF across all available formats.

Open Live Calculator →

Llama-3-monika-ddlc-11.5b-v1-i1-Q4_K_M-GGUF — Other Quantizations

Q4_K_M Current
68.57 GB
Advertisement Zone

Frequently Asked Questions

Can I run Llama-3-monika-ddlc-11.5b-v1-i1-Q4_K_M-GGUF Q4_K_M on a consumer GPU?
Running Llama-3-monika-ddlc-11.5b-v1-i1-Q4_K_M-GGUF Q4_K_M locally requires 68.57 GB VRAM, which exceeds consumer GPUs. You'll need prosumer cards like the NVIDIA A6000 (48GB) or an A100 (80GB).
What happens if I don't have enough VRAM?
If your GPU VRAM is insufficient, llama.cpp and similar tools will offload model layers to system RAM (CPU inference). This is much slower — expect 10-50× the generation latency compared to full GPU inference.
Can I use multiple GPUs to run Llama-3-monika-ddlc-11.5b-v1-i1-Q4_K_M-GGUF?
Yes! Tools like llama.cpp, vLLM, and Ollama support tensor parallelism across multiple GPUs. For example, 2× RTX 3090 (24GB each) gives you 48GB total VRAM, which can run many large models.
Is Q4_K_M quality good enough for production?
Q4_K_M is an excellent balance of quality and performance. Perplexity tests show minimal degradation (< 2%) vs FP16 for most models. Suitable for most production applications.