Skip to main content
Watch: Grok Bot Built My AI Video Arena While I Tested 8 Models

LOCAL MODELS

21 items

20 posts, 1 tool

Blog
Speed Up a Local LLM: The Agent Skill That Computes the Ceiling First

A new open-source agent skill hill-climbs local LLM serving speed. Its method - ceiling first, one change at a time, interleaved controls - is worth stealing even if you never install it.

Blog
Run DeepSeek V4 Flash 284B on 64GB RAM? llama-modchip Reality Check

llama-modchip claims DeepSeek-V4-Flash 284B fits in 64GB of RAM with no GPU. What the repo says, vendor-reported speeds, what Hacker News could not reproduce, and when a hosted model wins.

Blog
Ripple-65B: A Dense US Open-Weight Coding Model

Ricursive released Ripple-65B Preview, an Apache 2.0 dense model claiming US open-weight SOTA on Terminal-Bench 2.1. What the model card actually says, why HN pushed back, and who should test it.

Blog
GVS5H: Can Qwen3.8-27B Match Fable 5 on Coding?

GVS5H claims five Qwen3.8-27B instances match Fable 5 on LiveCodeBench Hard. What the harness does, why Hacker News doubts the benchmark, and what to copy.

Blog
Flint on Ollama: Best Local Coding LLM for Claude Code?

Recursive's Flint is a 40B open-weight coding model with 2.5B active parameters. How to run it on Ollama and point Claude Code at it, plus the benchmark caveats.

Blog
How much VRAM do you need to run a local LLM in 2026?

How much VRAM a local LLM needs: Q4 weights are about 30% of BF16, plus a KV cache that grows per token. Real numbers from 8 GB to 256 GB.

Blog
Local LLM Speed by Hardware: What llmspeed Gets Right

llmspeed estimates tokens per second for 30 machines and 15 models. What its numbers mean, the memory-bandwidth rule behind them, and why prefill matters for coding agents.

Blog
Ollama Decision Models: Run Nimble Locally with --ask

Ollama 0.40.4 runs decision models locally: ollama run nimble --ask answers yes/no, label and score questions with probabilities. Commands and limits.

Blog
Anthropic Self-Replicating AI Research: What Small Models Can Actually Do

Anthropic's Frontier Red Team says small open models may be months from self-replicating across cheap IoT devices. What it measured and where the claim is thin.

Blog
RTX Spark for Local LLMs: Will It Run a Coding Agent?

RTX Spark laptops ship October 16 with up to 128 GB of unified memory. Why the 600 GB/s figure is not memory bandwidth and which local coding models fit.

Blog
How to Run Kolibri Locally: GGUF, MLX and Hardware Picks

Kolibri 1 runs locally from 28.6 GB (Q2_K) to 83.1 GB (Q8_0). Which quant fits your RAM or Mac, measured speeds, and why Ollama cannot load it yet.

Blog
Run Qwen3.8-Flash-Next on a Gaming PC With Strata

Run Qwen3.8-Flash-Next locally with Strata on a 12 GB GPU: hardware needs, speeds by quant, the license catch, and when the hosted API is the better call.

Blog
Jeff: Jev-Style Decision Models Trained at Home on One GPU

Jeff fine-tunes Qwen3.5 and Gemma 4 into small Jev-compatible decision models on one GPU. The numbers, run commands, and where the benchmark misses real work.

Blog
Qwen3.8-27B vs Opus 4.6 Max: Local Agentic Coding Benchmarks

Qwen3.8-27B is a 27B dense Apache-2.0 model that beats Opus 4.6 Max on SWE-bench Pro (61.7 vs 53.4). Benchmarks, hardware, cost and when to run it.

Blog
Ornith-1.0: What an Open Source Self-Improving Coding Model Actually Means

Ornith-1.0 open-source coding models explained: what "self-improving" really means, the four model sizes, hardware needs, HN reactions and whether to try it.

Blog
Mellum2 Developer Guide: JetBrains' Open-Source Coding Model

Mellum2 developer guide: JetBrains' open-source 12B MoE coding model with 2.5B active parameters. How to run it locally and where it fits in your coding stack.

Blog
Forge Shows the Local Agent Reliability Gap Is a Harness Problem

Forge makes small local models more reliable at tool-calling with a harness that catches structural failures, retries intelligently and controls context.

Blog
Free Claude Code Is Really a Model Gateway Bet

The trending Free Claude Code repo is not just about avoiding API bills. It points at a bigger developer-tool pattern: model gateways for AI coding agents.

Blog
KV Caching: A Practical Guide to Optimizing Transformer Inference

How KV caching speeds up LLM inference - the math, the code, the memory tradeoffs, and when it stops helping. Every dev running local models hits this wall.

Blog
Qwen3.6-27B Is the Local Coding Model to Test First

Qwen3.6-27B is the local coding model to benchmark first: what hardware it needs, which jobs it should take over, and where a frontier API still wins.

Page 1 of 2Next
AI Development Stack

Get Smarter About AI Dev

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.

One email per weekReal code, not theoryFree forever