# whichllm | andy | Knowledge Base | Instagit

Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.

GitHub Stars: 3.9k

Repository: https://github.com/Andyyyy64/whichllm

---

## Articles

### [How to Display Detected Hardware Using WhichLLM](/Andyyyy64/whichllm/how-to-display-detected-hardware-using-whichllm)

Learn how to display detected hardware using WhichLLM. This guide shows you how to import and call functions to easily view GPU, CPU, RAM, and OS details.

- Tags: how-to-guide
- Published: 2026-06-10

### [How to Download and Chat with a Model Using the WhichLLM Run Command](/Andyyyy64/whichllm/how-to-download-and-chat-with-a-model-using-whichllm-run-command)

Easily download and chat with LLMs using the whichllm run command. This tool handles downloads, dependencies, and launches chat sessions instantly. Get started now!

- Tags: how-to-guide
- Published: 2026-06-10

### [How to Compare GPU Upgrade Options with WhichLLM: A Complete Guide](/Andyyyy64/whichllm/how-to-compare-gpu-upgrade-options-with-whichllm)

Compare GPU upgrade options with WhichLLM. Simulate graphics cards to see how they impact language model recommendations, quality, and inference speed. Optimize your hardware now.

- Tags: how-to-guide
- Published: 2026-06-10

### [Complete Guide to WhichLLM CLI Commands: Usage and Examples](/Andyyyy64/whichllm/what-are-the-available-whichllm-cli-commands)

Discover WhichLLM CLI commands like default, plan, upgrade, run, snippet, and hardware. Learn hardware detection, model ranking, and interactive execution with this comprehensive guide.

- Tags: how-to-guide
- Published: 2026-06-10

### [Bytes per Weight Values for Quantization Types in WhichLLM: Complete Reference Guide](/Andyyyy64/whichllm/what-are-the-bytes-per-weight-for-different-quantization-types-in-whichllm)

Discover bytes per weight for WhichLLM quantization types. This guide details the QUANT_BYTES_PER_WEIGHT constant for accurate model storage and VRAM calculations.

- Tags: api-reference
- Published: 2026-06-10

### [How WhichLLM's Ranking Engine Scores Models: The Complete Algorithm Guide](/Andyyyy64/whichllm/how-does-whichllms-ranking-engine-score-models)

Discover how WhichLLM's ranking engine scores models using seven signals including benchmarks speed and popularity. Understand the complete algorithm to find optimal LLM variants for your hardware.

- Tags: deep-dive
- Published: 2026-06-10

### [What Is the TTL for WhichLLM's Model Cache? A 6-Hour Technical Deep Dive](/Andyyyy64/whichllm/what-is-the-ttl-for-whichllms-model-cache)

Discover the exact 6-hour TTL for WhichLLM's model cache, detailed in src/whichllm/models/cache.py. Understand cache expiration for optimal performance.

- Tags: deep-dive
- Published: 2026-06-10

### [How Does WhichLLM Group Similar LLM Models? A Two-Pass Clustering Approach](/Andyyyy64/whichllm/how-does-whichllm-group-similar-llm-models)

Discover how WhichLLM groups similar LLM models with its innovative two-pass clustering approach. It leverages Hugging Face metadata and name normalization for accurate model family identification.

- Tags: internals
- Published: 2026-06-10

### [What Parameters Does WhichLLM Extract from HuggingFace Models?](/Andyyyy64/whichllm/what-parameters-does-whichllm-extract-from-huggingface-models)

Discover what parameters WhichLLM extracts from HuggingFace models, including technical specs, licensing, popularity, quantization, and benchmarks. Access detailed ModelInfo.

- Tags: deep-dive
- Published: 2026-06-10

### [How to Use the WhichLLM GPU Simulator for Planning: Complete Guide with Code Examples](/Andyyyy64/whichllm/how-to-use-whichllm-gpu-simulator-for-planning)

Plan LLM deployments with the WhichLLM GPU simulator. Emulate any GPU configuration virtually, saving costs and ensuring compatibility before hardware purchase. Get the complete guide with code.

- Tags: how-to-guide
- Published: 2026-06-10

### [What CPU Information Does WhichLLM Gather? A Technical Deep Dive](/Andyyyy64/whichllm/what-information-does-whichllm-gather-about-the-cpu)

Discover what CPU info WhichLLM collects Including model name core count and instruction set support to optimize LLM deployment.

- Tags: deep-dive
- Published: 2026-06-10

### [Which Libraries Does WhichLLM Use for NVIDIA GPU Detection?](/Andyyyy64/whichllm/what-libraries-are-used-for-nvidia-gpu-detection-in-whichllm)

Discover which libraries WhichLLM uses for NVIDIA GPU detection. Learn how pynvml and nvidia-smi enable efficient GPU monitoring for your LLM projects.

- Tags: internals
- Published: 2026-06-10

### [How WhichLLM Detects GPU Hardware: Cross-Platform GPU Detection Explained](/Andyyyy64/whichllm/how-does-whichllm-detect-gpu-hardware)

Discover how WhichLLM detects GPU hardware on Linux, macOS, and Windows using a unified, OS-aware system. Get robust cross-platform hardware info.

- Tags: internals
- Published: 2026-06-10

### [How to Run a Specific LLM Model Using whichllm: A Complete Guide](/Andyyyy64/whichllm/how-to-run-a-specific-llm-model-using-whichllm)

Learn how to run a specific LLM model with whichllm. Effortlessly download, configure, and execute Hugging Face models in isolated environments with optimal settings.

- Tags: how-to-guide
- Published: 2026-06-09

### [How to Auto-Pick the Best LLM and Start a Chat with whichllm](/Andyyyy64/whichllm/how-to-auto-pick-the-best-llm-and-start-a-chat-with-whichllm)

Effortlessly auto pick the best LLM for your hardware and start a chat with whichllm. Detect capabilities and launch optimal local LLMs with a single command.

- Tags: how-to-guide
- Published: 2026-06-09

### [How to Set a Minimum Speed Requirement for LLM Selection in whichllm](/Andyyyy64/whichllm/how-to-set-a-minimum-speed-requirement-for-llm-selection-in-whichllm)

Control whichllm LLM selection with a minimum speed requirement. Use the --min-speed flag or min_speed argument to set your tokens per second floor and optimize performance.

- Tags: how-to-guide
- Published: 2026-06-09

### [How to Specify Quantization Type in whichllm: A Complete Guide to the `--quant` Flag](/Andyyyy64/whichllm/how-to-specify-quantization-type-in-whichllm-commands)

Learn to specify quantization type in whichllm using the --quant flag. Filter, plan, run models, and generate Python snippets with formats like Q4_K_M and INT8.

- Tags: how-to-guide
- Published: 2026-06-09

### [How to Filter LLM Rankings by Direct Benchmark Evidence in whichllm](/Andyyyy64/whichllm/how-to-filter-llm-rankings-by-direct-benchmark-evidence-in-whichllm)

Filter whichllm rankings by direct benchmark evidence using strict CLI flags This ensures reliable LLM performance data from trusted sources like the Open LLM Leaderboard

- Tags: how-to-guide
- Published: 2026-06-09

### [How Does whichllm Generate Synthetic GGUF Variants for LLMs? A Code-Level Breakdown](/Andyyyy64/whichllm/how-does-whichllm-generate-synthetic-gguf-variants-for-llms)

Discover how whichllm creates synthetic GGUF variants from Safetensors files by estimating sizes, enabling better LLM model ranking even without real GGUF conversions. Get the code-level details.

- Tags: internals
- Published: 2026-06-09

### [WhichLLM Model Normalization: Complete List of Suffixes Stripped from Model IDs](/Andyyyy64/whichllm/what-suffixes-does-whichllm-remove-for-model-normalization)

Discover the 13 model suffixes WhichLLM strips for normalization including quantisation markers precision flags and variant tags to group related models.

- Tags: api-reference
- Published: 2026-06-09

### [How whichllm Groups and Deduplicates LLM Model Variants: A Deep Dive into the Source Code](/Andyyyy64/whichllm/how-does-whichllm-group-and-deduplicate-llm-model-variants)

Discover how whichllm groups and deduplicates LLM model variants. Explore source code to understand identifier normalization, grouping by base models, and merging benchmarks for a cleaner CLI experience.

- Tags: deep-dive
- Published: 2026-06-09

### [How Inference Speed Affects whichllm Model Rankings](/Andyyyy64/whichllm/how-does-inference-speed-affect-whichllms-model-rankings)

Discover how inference speed impacts whichllm model rankings. Learn how speed scores and filters affect LLM performance evaluations in the whichllm repository.

- Tags: performance
- Published: 2026-06-09

### [How WhichLLM Accounts for Quantization When Ranking Models: A Technical Deep Dive](/Andyyyy64/whichllm/how-does-whichllm-account-for-quantization-when-ranking-models)

Discover how WhichLLM ranks models by accounting for quantization. Learn about variant discovery, weight estimation, and quality penalty application for precise scoring.

- Tags: deep-dive
- Published: 2026-06-09

### [What Is Lineage in WhichLLM’s Ranking System? Recency-Aware Scoring for Model Families](/Andyyyy64/whichllm/what-is-lineage-in-whichllms-ranking-system)

Discover how WhichLLM's lineage system uses recency-aware scoring to fairly rank model families, avoiding penalties for older generations and highlighting new releases.

- Tags: deep-dive
- Published: 2026-06-09

### [How whichllm Simulates GPUs for Testing LLM Performance](/Andyyyy64/whichllm/how-does-whichllm-simulate-gpus-for-testing-llm-performance)

Discover how whichllm simulates GPUs to test LLM performance. Evaluate LLM compatibility and speed estimates using synthetic GPUInfo without physical hardware via --gpu and --vram flags.

- Tags: how-to-guide
- Published: 2026-06-09