Axiomi.si
Submit a tool

// guides · 50 articles

Guides

Original, hands on guides from the Axiomi editors: comparisons, “best tool for the job” roundups and plain English explainers.

  1. Explainers · 9 min readListen

    What Is Safetensors? Safe Model Files Explained

    What is safetensors? A plain guide to the Hugging Face model file format: why it is safer than pickle, how it compares to GGUF, and how to load or convert it.

  2. How to · 9 min readListen

    How to Use TensorFlow in Jupyter Notebook

    How to use TensorFlow in Jupyter Notebook: install it in a venv, register the kernel with ipykernel, pick it in JupyterLab or VS Code, and fix common errors.

  3. Comparisons · 9 min readListen

    Ollama vs vLLM: Which Should You Run?

    Ollama vs vLLM compared: setup, model formats, speed for one user or many, hardware, Mac support and the signs it is time to move from Ollama to vLLM.

  4. How to · 8 min readListen

    How to Run ComfyUI on Mac (Apple Silicon)

    How to run ComfyUI on Mac: install Comfy Desktop or set it up by hand with PyTorch and Metal, where model files go, what fits in memory and how to fix errors.

  5. Explainers · 9 min readListen

    RTX 3090 BF16 at Full Rate: What It Means for AI

    RTX 3090 BF16 runs at half rate, and a new Linux mod restores it on RTX 30 cards. What it speeds up for local LLMs, what it doesn't, the risks and setup.

  6. Comparisons · 9 min readListen

    Tinygrad vs MLX: Which Should You Use?

    Tinygrad vs MLX compared for Apple silicon and beyond: hardware support, lazy graphs, JIT and compile, LLM tooling, install and which framework fits your project.

  7. How to · 9 min readListen

    How to Run DeepSeek V4.1 Flash Locally

    Can you run DeepSeek V4.1 Flash locally? Real RAM, VRAM and disk needs by GGUF, Strata on one 12 GB GPU, the llama.cpp PR, vLLM, Ollama and DGX Spark.

  8. Comparisons · 9 min readListen

    SmolLM vs Llama: Which 3B Model Should You Run?

    SmolLM vs Llama compared on benchmarks, licence, context, languages, memory and local setup, so you can choose between SmolLM3 and Llama 3.2 for your project.

  9. Comparisons · 9 min readListen

    SGLang vs vLLM on DGX Spark: Which to Use?

    SGLang vs vLLM on DGX Spark compared on setup, memory, NVFP4 models, speed and clustering, so you can pick the right server for your GB10 desktop.

  10. How to · 9 min readListen

    Recursive Flint: Run the 40B Coding Model Locally

    Recursive Flint is an Apache 2.0 coding model with 40B total and 2.5B active parameters. How to run Flint locally with Ollama, llama.cpp, rec or Unsloth.

  11. Comparisons · 8 min readListen

    SmolLM vs Gemma: Which Small Model to Use?

    SmolLM vs Gemma compared on size, licence, context, languages, vision and audio, local setup and fine tuning, so you can pick the right small model in 2026.

  12. How to · 9 min readListen

    MOSS-Image: Run It Locally in ComfyUI

    MOSS-Image is an Apache 2.0 open weight 5B text to image model built for text and layouts. How to run MOSS-Image in ComfyUI, file sizes and best settings.

  13. Best of · 8 min readListen

    Best LLM Pretraining Dataset in 2026: Top Picks

    The best LLM pretraining dataset depends on your goal. FineWeb-Edu for small models, DCLM-Baseline and Nemotron-CC for scale, Common Pile for licensed text.

  14. Explainers · 6 min readListen

    What Is DeepInfer? DeepSeek's Engine vs vLLM

    DeepInfer is DeepSeek's open source engine for DeepSeek-V4.1-Flash. What it does, the hardware it needs, what is missing, and when vLLM or SGLang fits better.

  15. How to · 8 min readListen

    LLM Distillation vs Quantization: Key Differences

    LLM distillation vs quantization: distillation trains a smaller student model, quantization stores the same weights in fewer bits. When to use each, or both.

  16. How to · 8 min readListen

    Best Local LLM for Image Generation in 2026

    The best local LLM for image generation is really an open image model. Our picks by GPU and license: FLUX 3 Klein, Z-Image Turbo, Qwen-Image 2.1 and more.

  17. How to · 9 min readListen

    FLUX Open Weights: Every Model and Its License

    FLUX open weights explained: every Black Forest Labs model you can download, its license, file size and VRAM, plus how to run FLUX 3 Klein in ComfyUI.

    · updated

  18. Explainers · 10 min readListen

    What Is Mechanistic Interpretability Research?

    What is mechanistic interpretability research? A plain guide to features, circuits, superposition, sparse autoencoders, key papers, open tools and how to start.

    · updated

  19. Best of · 8 min readListen

    Best ML Frameworks for Python in 2026

    The best ML frameworks for Python in 2026, ranked by job: PyTorch, scikit-learn, JAX, Keras 3, XGBoost, LightGBM, TensorFlow, MLX and more, with versions.

    · updated

  20. How to · 9 min readListen

    How to Run Muse Spark Open Locally (816B MoE)

    Can you run Muse Spark Open locally? Real memory needs by quant (GGUF, MLX, NVFP4), llama.cpp and MLX commands, Mac Studio setups, licence terms and limits.

  21. How to · 7 min readListen

    How to Run LFM2.5 24B Locally

    Run Liquid AI LFM2.5-24B-A2B locally with Ollama, llama.cpp or MLX: VRAM by quant, Q4_K_M sizes, Ollama 0.17.1 caveat, sampling settings and agent tips.

    · updated

  22. Comparisons · 9 min readListen

    Tinygrad vs PyTorch Performance

    Tinygrad vs PyTorch performance: when TinyJit and BEAM can outrun eager PyTorch, when torch.compile and the ecosystem win, and how to compare them fairly.

  23. How to · 8 min readListen

    How to Use TensorFlow in Python (Step by Step)

    How to use TensorFlow in Python in 2026: install it in a venv, work with tensors and gradients, train a Keras model, feed data with tf.data and save it.

  24. How to · 9 min readListen

    How to Use TensorFlow with GPU (2026 Setup)

    How to use TensorFlow with GPU in 2026: the pip [and-cuda] install on Linux and WSL2, Docker, Mac Metal, how to verify the GPU, and fixes for common errors.

  25. How to · 9 min readListen

    How to Fine Tune an LLM for Code Generation

    How to fine tune an LLM for code generation: pick a coder base model, build an instruction or FIM dataset, train a LoRA with TRL or Unsloth, test with pass@k.

  26. How to · 8 min readListen

    How to Run DeepSeek Locally with Ollama

    Run DeepSeek Locally with Ollama: pick R1 distill tags by download size, set context length, handle thinking output, and know when 671B V3 is server only.

    · updated

  27. Comparisons · 7 min readListen

    TensorFlow vs PyTorch vs Keras in 2026

    TensorFlow vs PyTorch vs Keras in 2026: Keras 3 multibackend, which is easier to learn, open weight LLM ecosystem fit, and who should pick each stack.

  28. How to · 8 min readListen

    How to Run Qwen 3.6 Locally (VRAM + Setup)

    Run Qwen 3.6 locally with Ollama, llama.cpp or LM Studio: pick 27B or 35B-A3B by VRAM, thinking mode, vision tips, MTP speedups and sampling settings.

  29. How to · 8 min readListen

    How to Run Gemma 4 Locally (VRAM + Setup)

    Run Gemma 4 locally with Ollama, llama.cpp or LM Studio: pick E2B, E4B, 12B, 26B-A4B or 31B by memory, thinking mode, vision tips and sampling settings.

    · updated

  30. How to · 7 min readListen

    How to Use Local LLM in VS Code

    Wire a local LLM into VS Code with Ollama: official Chat extension, Continue.dev for tab complete, model picks by VRAM, and privacy tips for offline coding.

  31. How to · 7 min readListen

    How to Quantize LLM Models

    Practical how to quantize LLM models: llama.cpp convert then Q4_K_M, Hugging Face bitsandbytes 4 bit loads, Ollama GGUF import, and when to use each path.

  32. Best of · 10 min readListen

    Open Source LLM Models to Run Locally

    Open source LLM models to run locally: match Qwen3, Gemma 4, gpt-oss and DeepSeek R1 distill tags to your VRAM, with Ollama setup and licence caveats.

    · updated

  33. How to · 10 min readListen

    How to Run Bonsai 2 27B Locally (Ternary GGUF)

    Run Prism ML's ternary Bonsai 2 27B locally: why stock llama.cpp, Ollama and LM Studio can't load it, PQ2_0 vs PTQ1_0, memory needs, setup steps and settings.

  34. How to · 8 min readListen

    EmbeddingGemma 2: How to Use It Locally

    How to run Google's EmbeddingGemma 2 locally: setup with Sentence Transformers, task prefixes, Matryoshka truncation, GGUF and MLX builds, and memory needs.

  35. How to · 8 min readListen

    How to Run Qwen 3.8 27B Locally (VRAM + Setup)

    Run Qwen 3.8 27B locally with Ollama, llama.cpp, LM Studio or vLLM: which quant fits 8, 16 or 24 GB, setup commands, thinking controls and context memory.

  36. Comparisons · 10 min readListen

    SGLang vs vLLM vs llama.cpp: Which to Use?

    SGLang vs vLLM vs llama.cpp compared: what SGLang is, how RadixAttention works, Docker setup, independent benchmarks, hardware and when to pick each.

    · updated

  37. Comparisons · 9 min readListen

    Ollama vs llama.cpp vs LM Studio: 2026 Guide

    Ollama vs llama.cpp vs LM Studio compared for 2026: what each one is, ports, licences, Mac and GPU support, the context length trap, and which to pick.

    · updated

  38. How to · 9 min readListen

    Train a Small LLM From Scratch (nanochat, Megatron-LM)

    Train a small LLM from scratch with nanochat, and learn when NVIDIA Megatron-LM fits: model sizes, budgets, datasets, compute math and multi GPU parallelism.

    · updated

  39. Comparisons · 9 min readListen

    Neuronpedia Guide: TransformerLens vs nnsight

    Neuronpedia explained (SAE features, Jacobian Lens, circuit tracer, API) and TransformerLens vs nnsight compared: TransformerLens 4, nnsight 0.8 and NDIF.

    · updated

  40. Comparisons · 6 min readListen

    PyTorch vs JAX in 2026: Which Should You Learn?

    PyTorch vs JAX in 2026: how eager PyTorch and functional JAX differ, hardware support, the LLM ecosystem, TPUs and TorchTPU, and which framework fits your work.

    · updated

  41. Explainers · 6 min readListen

    Speculative Decoding vs MTP: Faster LLM Output

    Speculative decoding vs MTP explained: how draft models, EAGLE-3, MTP heads and DFlash speed up LLM output, and how to enable each in llama.cpp, vLLM or SGLang.

  42. Explainers · 7 min readListen

    Open Weight vs Open Source AI: The Difference

    Open weight vs open source AI explained: what the OSI definition requires, which popular models are which, and a licence table checked against model cards.

  43. Comparisons · 7 min readListen

    MLX vs GGUF on Mac: Which Should You Use?

    MLX vs GGUF on a Mac: what each format is, how Ollama and LM Studio use them, speed tradeoffs, memory limits, fine tuning with mlx-lm, and which to download.

  44. Explainers · 7 min readListen

    LoRA vs QLoRA vs DoRA: Which Fine Tuning Method?

    QLoRA vs LoRA explained, plus DoRA and full fine tuning: how each works, real VRAM figures, quality tradeoffs, recommended settings, and when to choose which.

  45. Explainers · 7 min readListen

    KV Cache Quantization: Fit Longer Context in VRAM

    KV cache quantization explained: how q8_0, q4_0 and FP8 caches cut memory, the settings for llama.cpp, Ollama, LM Studio, vLLM and MLX, and when quality drops.

  46. How to · 6 min readListen

    How to Run gpt-oss Locally (20b and 120b)

    Run gpt-oss locally with Ollama, LM Studio, llama.cpp or vLLM: memory needs for 20b and 120b, setup commands, reasoning effort, harmony format and fine tuning.

  47. How to · 8 min readListen

    How to Fine Tune an LLM Locally in 2026

    Fine tune an LLM locally, step by step: when it pays off, picking a base model, formatting data, Unsloth vs Axolotl vs TRL vs mlx-lm, training and GGUF export.

  48. Explainers · 8 min readListen

    How Much VRAM Do I Need for an LLM?

    How much VRAM do you need for an LLM? A simple formula for weights plus KV cache, worked examples from real model configs, and what fits in 8, 16, 24 or 32 GB.

  49. Explainers · 7 min readListen

    GRPO vs PPO: How LLM RL Training Differs

    GRPO vs PPO explained simply: how each trains LLMs with rewards, why GRPO drops the critic, what DAPO and Dr. GRPO changed, and when to pick GRPO, PPO or DPO.

  50. Explainers · 7 min readListen

    GGUF Quantization Explained: Pick the Right Quant

    GGUF quantization explained in plain English: what Q4_K_M, Q8_0 and IQ quants mean, real bits per weight numbers, GGUF vs safetensors, and which file to pick.