The Bloke Q5_K_M 55B Parameters

VRAM Requirements for
SG-Raccoon-Yi-200k-2.0-GGUF Q5_K_M

To run SG-Raccoon-Yi-200k-2.0-GGUF locally at Q5_K_M quantization, you need at minimum 40.71 GB of GPU VRAM.

40.71 GB
Required VRAM
37.81 GB
File Size
8K tokens
Context Window
55B
Parameters
Estimated VRAM Required
40.71
GB
Prosumer / Workstation
0 16GB
RTX 3080 48GB
A6000 80GB+

Recommended GPU Configurations

Budget $1,200 – $1,800

2× RTX 3090 (48GB total)

48 GB

Dual-GPU via tensor parallelism. Best cost per GB at this tier.

Balanced $4,000 – $5,500

NVIDIA A6000 (48GB)

48 GB

Single-card 48GB pro GPU. Clean setup, no multi-GPU overhead.

⚠️ 0.7 GB short
Ultimate $8,000 – $12,000

NVIDIA A100 40GB SXM

40 GB HBM2e

Data-centre HBM2e bandwidth. Dramatically faster throughput.

📊 VRAM Calculation Breakdown

Model File Size (Q5_K_M) 37.81 GB
Context Overhead (8,192 tokens × 55B × 2 ÷ 1M) 0.901 GB
System Buffer (OS + CUDA runtime) 2.00 GB
Total Required VRAM 40.71 GB

Try a Different Quantization

Use the interactive calculator to compare SG-Raccoon-Yi-200k-2.0-GGUF across all available formats.

Open Live Calculator →

SG-Raccoon-Yi-200k-2.0-GGUF — Other Quantizations

Q2_K 17.19 GB file
20.09 GB
Q3_K_L 24.06 GB file
26.96 GB
Q3_K_M 24.06 GB file
26.96 GB
Q3_K_S 24.06 GB file
26.96 GB
Q4_0 30.94 GB file
33.84 GB
Q4_K_M 30.94 GB file
33.84 GB
Q4_K_S 30.94 GB file
33.84 GB
Q5_0 37.81 GB file
40.71 GB
Q5_K_M Current
40.71 GB
Q5_K_S 37.81 GB file
40.71 GB
Q6_K 44.69 GB file
47.59 GB
Advertisement Zone

Frequently Asked Questions

Can I run SG-Raccoon-Yi-200k-2.0-GGUF Q5_K_M on a consumer GPU?
Running SG-Raccoon-Yi-200k-2.0-GGUF Q5_K_M locally requires 40.71 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 SG-Raccoon-Yi-200k-2.0-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 Q5_K_M quality good enough for production?
Q5_K_M is suitable for specialized use cases. Check community benchmarks for specific quality metrics.