This guide outlines the most effective approach for running large language models locally on hardware with 24GB of VRAM. It advises moving away from squeezing extremely large parameter models toward using high-performance 20B to 35B class models that allow room for context and fast processing speeds. The article explains how memory is allocated across model weights, KV cache, and runtime overhead while recommending specific top performers:
* Qwen3.6-27B for agentic coding
* Qwen3.6-35B-A3B MoE for speed in general conversation
* Gemma 4 26B for multimodal and multilingual support
* Mistral Small 3.2 24B as a low-latency assistant
* gpt-oss-20b for structured reasoning tasks
* DeepSeek-R1-Distill-Qwen-32B for deep logical reasoning through chain of thought
* Qwen3.6-27B for agentic coding
* Qwen3.6-35B-A3B MoE for speed in general conversation
* Gemma 4 26B for multimodal and multilingual support
* Mistral Small 3.2 24B as a low-latency assistant
* gpt-oss-20b for structured reasoning tasks
* DeepSeek-R1-Distill-Qwen-32B for deep logical reasoning through chain of thought
This article explores the feasibility of running Large Language Models (LLMs) locally using only a CPU, challenging the assumption that expensive GPUs are strictly necessary. By testing eight different models on an older Intel i5 laptop with 12GB of RAM via Ollama, the author identifies which models offer practical usability for everyday tasks.
Key points include:
- Using tokens per second as a more critical metric for usability than model size or RAM usage alone.
- Why 1B to 2B parameter models provide the best balance of responsiveness and reasoning on low-end hardware.
- The effectiveness of GGUF quantization (specifically Q4_K_M) in reducing resource demands.
- A comparison of various model tiers, from ultra-fast tiny models like Qwen 0.6B to slower, high-capability models like Ministral 3 8B.
Key points include:
- Using tokens per second as a more critical metric for usability than model size or RAM usage alone.
- Why 1B to 2B parameter models provide the best balance of responsiveness and reasoning on low-end hardware.
- The effectiveness of GGUF quantization (specifically Q4_K_M) in reducing resource demands.
- A comparison of various model tiers, from ultra-fast tiny models like Qwen 0.6B to slower, high-capability models like Ministral 3 8B.
This guide helps engineers build and ship LLM products by covering the full technical stack. It moves from core mechanics (tokenization, embeddings, attention) to training methodologies (pretraining, SFT, RLHF/DPO) and deployment optimizations (LoRA, quantization, vLLM). The focus is on managing critical production tradeoffs between accuracy, latency, memory, and cost
This article details benchmarks for Unsloth Dynamic GGUFs of the Qwen3.5 model, including analysis of perplexity, KL divergence, and MXFP4. It covers performance across different bit widths and quant types, highlighting the impact of Imatrix and the limitations of certain quantization approaches. Full benchmark data is also provided.
Qwen3-Coder-Next is an 80B MoE model with 256K context designed for fast, agentic coding and local use. It offers performance comparable to models with 10-20x more active parameters and excels in long-horizon reasoning, complex tool use, and recovery from execution failures.
A deep dive into the process of LLM inference, covering tokenization, transformer architecture, KV caching, and optimization techniques for efficient text generation.
This article details the performance of Unsloth Dynamic GGUFs on the Aider Polyglot benchmark, showcasing how it can quantize LLMs like DeepSeek-V3.1 to as low as 1-bit while outperforming models like GPT-4.5 and Claude-4-Opus. It also covers benchmark setup, comparisons to other quantization methods, and chat template bug fixes.
This document details how to run Qwen models locally using the Text Generation Web UI (oobabooga), covering installation, setup, and launching the web interface.
This article explains how to accurately quantize a Large Language Model (LLM) and convert it to the GGUF format for efficient CPU inference. It covers using an importance matrix (imatrix) and K-Quantization method with Gemma 2 Instruct as an example, while highlighting its applicability to other models like Qwen2, Llama 3, and Phi-3.
