Do Drafters Work on Small Models? Gemma 4 E2B and E4B on Two Small GPUs
This article provides a step by step guide to serving Gemma 4 E2B and E4B with Google's QAT assistant drafters through llama.cpp's speculative decod…
Architecture
⚑ Сообщить о проблемеПоследние новости Architecture от Tech News
Все темы
agents
ai
api
architecture
automation
aws
backend
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
news
opensource
performance
productivity
programming
python
react
security
showdev
softwareengineering
systemdesign
tutorial
typescript
webdev
Gemma 4's MTP Drafter, Explained: Speculative Decoding and a 4-Bit Drafter at 60% of the Size
This article provides a step by step introduction to speculative decoding with Gemma 4's multi-token prediction (MTP) drafter, served by llama.cpp o…
Inside My llama.cpp Setup: Tuning Qwen 3.8 27B for 512K Context
Understanding My llama.cpp Qwen 3.8 Configuration I've been tuning llama.cpp for local AI development, and the command line can quickly become a col…
llama.cpp vs Ollama in 2026: Which Runtime Should You Run?
Ollama and llama.cpp are often compared as if they were rival inference engines. The real choice is between a managed model service and a toolkit yo…
Two Rust Clients for Gemma 4: Calling the Endpoint vs. Calling the MCP Server 🦀
This article provides a step by step guide to two small Rust CLIs that ask a self-hosted Gemma 4 E2B the same question. The first calls the model's…
KV Cache on 16 GB GPUs: Making Long Context Actually Fit
A model can advertise a 128K context window and still fail at 40K tokens on a 16 GB GPU. The architecture ceiling never promised that weights, KV ca…
Gemma 4 on an 2021 4 GB Laptop GPU: QAT Takes It From 9.5 GiB to 1.6
This article provides a step by step deployment guide for Gemma 4 E2B's quantization-aware-trained (QAT) checkpoint to a local, laptop hosted GPU en…
Fix Local LLM Quality: Context Stacking & Rope Freq Tweaks
This article was originally published on BuildZn . Everyone's running local LLMs now, which is great. But then they hit the wall: "Why does my 7B mo…
"V cache quantization requires flash_attn" — the llama.cpp error that quietly halves your context window
I did not meet this error while debugging a crash. I met it while writing a calculator. llama_context: quantized V cache requires flash_attn to be e…
Running a 1.5B-Parameter LLM Entirely On-Device for Mental Health — The NilaMind Architecture
How I built a mental health companion that never connects to the internet, and why the most important safety decisions have nothing to do with the A…
How fast is LlamaStash? Overhead, throughput, and a fair comparison with Ollama and LM Studio
Originally published at deepu.tech . In my release post for LlamaStash I made a claim I need to back up. The wrapper adds zero overhead vs running l…
Qwen 3.6 27B and 35B MTP vs Standard on 16GB GPU
I tested Speculative decoding (Multi-Token Prediction, MTP) performance in Qwen 3.6 27B and 35B on an RTX 4080 with 16 GB VRAM. For a broader view o…