LLM guides
Pick a guide for inference, fine-tuning or GPU costs. Every guide has a prompt you can copy or download for your coding agent.
Only the linked gpt-oss / RunPod configuration has a live inference smoke test. Source-reviewed guides are not GPU-tested; fine-tuning and cost guides are planning resources.
Inference and fine-tuning
-
Get prompt
Run gpt-oss-120b on RunPod
Start an inference endpoint and check its response. Tested on one A100 80GB configuration.
One configuration smoke-tested -
Get prompt
Best cloud GPU for fine-tuning
Compare GPU rental costs and plan a bounded LoRA or QLoRA test. Not a tested training recipe.
Planning guide · not GPU-tested
Model deployment guides
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
- Get prompt
-
Get prompt
Nemotron 3 Super 120B-A12B
vLLM inference. Choose from 7 provider guides.
Source-reviewed · not GPU-tested -
Get prompt
Nemotron 3 Ultra 550B-A55B
vLLM inference. Choose from 7 provider guides.
Source-reviewed · not GPU-tested - Get prompt
- Get prompt
GPU and hosting cost guides
-
Get prompt
Cheapest GPU for GLM-4.7-Flash
Compare rental prices for a quantized GLM-4.7-Flash setup; verify the exact checkpoint and memory fit.
Planning guide · not GPU-tested -
Get prompt
Best GPU for Kimi Linear 48B hosting
Price a quantized Kimi Linear 48B setup, with separate checks for context length and memory fit.
Planning guide · not GPU-tested -
Get prompt
Best GPU for Qwen3.6 35B-A3B hosting
Compare rental prices for quantized Qwen3.6 35B-A3B; memory estimates are not a tested configuration.
Planning guide · not GPU-tested -
Get prompt
Cheapest provider for batch inference
Compare 24GB+ GPU rental prices; validate model fit and measure batch throughput separately.
Planning guide · not GPU-tested -
Get prompt
H100 vs A100 for training cost
Compare H100-family and A100-family rental costs before choosing a training budget.
Planning guide · not GPU-tested -
Get prompt
Modal alternatives for vLLM inference
Compare tracked rental prices and provider tradeoffs. Not a throughput benchmark.
Planning guide · not GPU-tested -
Get prompt
Cheapest vLLM hosting by provider and GPU
Compare tracked rental prices and provider tradeoffs. Not a throughput benchmark.
Planning guide · not GPU-tested -
Get prompt
Modal vs RunPod vs Lambda vs Vast for vLLM hosting
Compare tracked rental prices and provider tradeoffs. Not a throughput benchmark.
Planning guide · not GPU-tested