Dev Quasar Q3_K_M 22B Parameters

VRAM Requirements for
Gryphe.Pantheon-RP-Pure-1.6.2-22b-Small-GGUF Q3_K_M

To run Gryphe.Pantheon-RP-Pure-1.6.2-22b-Small-GGUF locally at Q3_K_M quantization, you need at minimum 11.99 GB of GPU VRAM.

11.99 GB
Required VRAM
9.63 GB
File Size
8K tokens
Context Window
22B
Parameters
Estimated VRAM Required
11.99
GB
Mid-Range GPU Required
0 16GB
RTX 3080 48GB
A6000 80GB+

Recommended GPU Configurations

⚠️ 2.0 GB short
Budget $350 – $500

RTX 3080 (10GB)

10 GB

Used market gem. Tight on VRAM but viable for this workload.

Balanced $699 – $799

RTX 4070 Ti (12GB)

12 GB

Strong inference GPU. Handles 7-13B models comfortably.

Ultimate $1,599 – $1,999

RTX 4090 (24GB)

24 GB

Best consumer GPU. Breeze through 13B models at any quantization.

📊 VRAM Calculation Breakdown

Model File Size (Q3_K_M) 9.63 GB
Context Overhead (8,192 tokens × 22B × 2 ÷ 1M) 0.36 GB
System Buffer (OS + CUDA runtime) 2.00 GB
Total Required VRAM 11.99 GB

Try a Different Quantization

Use the interactive calculator to compare Gryphe.Pantheon-RP-Pure-1.6.2-22b-Small-GGUF across all available formats.

Open Live Calculator →

Gryphe.Pantheon-RP-Pure-1.6.2-22b-Small-GGUF — Other Quantizations

Q2_K 6.88 GB file
9.24 GB
Q3_K_L 9.63 GB file
11.99 GB
Q3_K_M Current
11.99 GB
Q3_K_S 9.63 GB file
11.99 GB
Q4_K_M 12.38 GB file
14.74 GB
Q4_K_S 12.38 GB file
14.74 GB
Q5_K_M 15.13 GB file
17.49 GB
Q5_K_S 15.13 GB file
17.49 GB
Q6_K 17.88 GB file
20.24 GB
Q8_0 23.38 GB file
25.74 GB
Advertisement Zone

Frequently Asked Questions

Can I run Gryphe.Pantheon-RP-Pure-1.6.2-22b-Small-GGUF Q3_K_M on a consumer GPU?
Yes! At 11.99 GB VRAM required, a single high-end consumer GPU like the RTX 4090 (24GB) can handle this workload. You can also use multiple GPUs for tensor parallelism.
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 Gryphe.Pantheon-RP-Pure-1.6.2-22b-Small-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 Q3_K_M quality good enough for production?
Q3_K_M is suitable for specialized use cases. Check community benchmarks for specific quality metrics.