Anthracite Org Q1_0 123B Parameters

VRAM Requirements for
magnum-v2-123b-gguf Q1_0

To run magnum-v2-123b-gguf locally at Q1_0 quantization, you need at minimum 127.02 GB of GPU VRAM.

127.02 GB
Required VRAM
123 GB
File Size
8K tokens
Context Window
123B
Parameters
Estimated VRAM Required
127.02
GB
Cluster Required
0 16GB
RTX 3080 48GB
A6000 80GB+

Recommended GPU Configurations

Budget $40,000+

4× A100 40GB Cluster

160 GB

Distributed inference across 4 A100s. Minimum viable cluster.

Balanced $60,000+

2× H100 80GB NVLink

160 GB HBM3

NVLink bridge enables unified 160GB VRAM pool.

Ultimate $3,000,000+

NVIDIA GB200 NVL72

1.4 TB HBM3e

Next-gen Grace Blackwell Superchip. Built for frontier models.

📊 VRAM Calculation Breakdown

Model File Size (Q1_0) 123 GB
Context Overhead (8,192 tokens × 123B × 2 ÷ 1M) 2.015 GB
System Buffer (OS + CUDA runtime) 2.00 GB
Total Required VRAM 127.02 GB

Try a Different Quantization

Use the interactive calculator to compare magnum-v2-123b-gguf across all available formats.

Open Live Calculator →

magnum-v2-123b-gguf — Other Quantizations

Q2_0 38.44 GB file
42.46 GB
Q3_0 53.81 GB file
57.83 GB
Q4_0 69.19 GB file
73.21 GB
Q5_0 84.56 GB file
88.58 GB
Q6_0 99.94 GB file
103.96 GB
Q1_0 Current
127.02 GB
FP16 246 GB file
250.02 GB
Advertisement Zone

Frequently Asked Questions

Can I run magnum-v2-123b-gguf Q1_0 on a consumer GPU?
Running magnum-v2-123b-gguf Q1_0 locally requires 127.02 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 magnum-v2-123b-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 Q1_0 quality good enough for production?
Q1_0 is suitable for specialized use cases. Check community benchmarks for specific quality metrics.