agentsclimarketplace

Coreweave cost tuning

Skill jeremylongshore/claude-code-plugins-plus-skills/plugins/saas-packs/coreweave-pack/skills/coreweave-cost-tuning

'Optimize CoreWeave GPU cloud costs with right-sizing and scheduling.From its SKILL.md

Install
npx -y skills add jeremylongshore/claude-code-plugins-plus-skills --skill coreweave-cost-tuning

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.2 KB, 473 tokens by cl100k_base, as published. Nobody here has run it

CoreWeave Cost Tuning

Community-contributed. Not affiliated with, endorsed by, or sponsored by CoreWeave, Inc. CoreWeave is a registered trademark of CoreWeave, Inc.

GPU Pricing Reference (approximate)

GPUPer GPU/hourBest For
A100 40GB PCIe~$1.50Development, smaller models
A100 80GB PCIe~$2.21Production inference
H100 80GB PCIe~$4.76High-throughput inference
H100 SXM5 (8x)~$6.15/GPUTraining, multi-GPU
L40~$1.10Image generation, light inference

Cost Optimization Strategies

Scale-to-Zero for Dev/Staging

autoscaling.knative.dev/minScale: "0"
autoscaling.knative.dev/scaleDownDelay: "5m"

Right-Size GPU Selection

def recommend_gpu(model_size_b: float, inference_only: bool = True) -> str:
    if model_size_b <= 7:
        return "L40" if inference_only else "A100_PCIE_80GB"
    elif model_size_b <= 13:
        return "A100_PCIE_80GB"
    elif model_size_b <= 70:
        return "A100_PCIE_80GB (4x tensor parallel)"
    else:
        return "H100_SXM5 (8x tensor parallel)"

Quantization to Use Smaller GPUs

Use AWQ or GPTQ quantization to fit larger models on smaller GPUs:

# 70B model at 4-bit fits on single A100-80GB instead of 4x
vllm serve meta-llama/Llama-3.1-70B-Instruct-AWQ --quantization awq

Resources

Next Steps

For architecture patterns, see coreweave-reference-architecture.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.