MergeKit: Combine LLM Models for Better Performance

MergeKit: Combine LLM Models for Better Performance

Model merging combines the weights of multiple fine-tuned models into one, inheriting the strengths of each. The result: a model that might have better coding ability from one source and better instruction following from another, without any additional training. MergeKit has made this accessible, and the top models on the Open LLM Leaderboard are often merges.

Hardware needed: Model merging is done on CPU/RAM — you need enough system RAM to hold all source models simultaneously. Merging two 7B FP16 models requires ~28GB RAM. For hardware recommendations including RAM capacity, see LLMHardware.io.

Merging Methods

SLERP (Spherical Linear Interpolation) merges two models at a specified interpolation ratio — simpler and more predictable. TIES-Merging handles multiple models by resolving sign conflicts between weight deltas. DARE uses dropout on weight deltas before merging to reduce interference. For beginners, SLERP at 0.5 (equal blend) is a good starting point. More advanced users experiment with TIES and DARE for merging 3+ models.

MergeKit Installation and Usage

Install: pip install mergekit. Define a merge config in YAML specifying source models and merge method. Run: mergekit-yaml merge_config.yml ./output-model. The output is a standard HuggingFace model directory you can quantize to GGUF with llama.cpp's conversion scripts. Many successful community merges are published on HuggingFace — browsing the top-rated models in the 7B range reveals merges often outperforming their constituent models.

Practical Tips

Only merge models with the same architecture and base model. You can't merge Llama 3 with Mistral. Merging a coding fine-tune with an instruction fine-tune of the same base model is the most reliably positive result. Always evaluate the merge on a standard test set before declaring it better — merges can introduce unexpected failure modes. The HuggingFace Model Card for merged models should document the source models and merge configuration for reproducibility.

Comments

Post a Comment

Popular posts from this blog

AMD RX 9070 XT for Local LLMs: ROCm Performance Guide (2026)

The AMD RX 9070 XT launched in early 2026 at $599 with 16GB GDDR6 and 648 GB/s memory bandwidth. For local LLM users who want a mid-range GPU without NVIDIA prices, this changes the calculus significantly. Here is what it actually delivers. RX 9070 XT Specs vs Competition GPU VRAM Bandwidth Price LLM Score RX 9070 XT 16 GB 648 GB/s $599 ~60 tok/s RTX 4070 Ti Super 16 GB 672 GB/s $799 ~62 tok/s RTX 4080 Super 16 GB 736 GB/s $999 ~68 tok/s RTX 4090 24 GB 1,008 GB/s ~$1,100 ~90 tok/s At $599 with 16GB VRAM, the RX 9070 XT is the best value GPU for local LLMs in the mid-range tier in 2026. See the full comparison at LLMHardware.io's AMD GPU guide . ROCm Setup on Linux (2026) # Ubuntu 22.04/24.04 sudo apt install rocm-hip-libraries hip-base # or use the AMD installer: wget https://repo.radeon.com/amdgpu-install/6.3/ubuntu/jammy/amdgpu-install_6.3.60300-1_all.deb sudo dpkg -i amdgpu-install*.deb sudo amdgpu-install --usecase=rocm,lrt,openclsdk # Verify ROCm sees your GPU r...
Read more

llama.cpp flash attention: how to enable and benchmark

Image
Flash attention computes attention with far less memory traffic. The math is identical; the memory movement is not. In llama.cpp it matters most in two situations: long context windows and tight video memory (VRAM). With flash attention enabled, the key-value cache shrinks substantially. A 32k-token context window becomes realistic on a 16GB card, and the prompt-processing phase speeds up, so long documents get ingested faster. The catch is compatibility: not every model and quantization combination supports it, and on some setups the speedup is modest. If you run short chats on a strong GPU, you may barely notice. Where it shines is retrieval-augmented generation (RAG) and long-document work on mid-range cards. Enable it, compare your tokens per second, and keep it if your workload benefits. For the common case of pasting a long PDF and asking questions, it is close to free performance. See how context length changes VRAM needs .
Read more

SillyTavern with Local LLMs: Complete Setup for AI Companions

Image
SillyTavern is the most feature-rich frontend for character-based AI conversations. What began as an AI roleplay tool has evolved into a powerful platform with persona management, memory systems, extensive prompt engineering tools, and connections to every major local inference backend. Here's how to set it up with local models. Quick connect: SillyTavern connects to Ollama, KoboldCpp, llama.cpp server, and TabbyAPI (ExLlamaV2) out of the box. Any of the hardware setups at LLMHardware.io provides a solid backend for SillyTavern. Installation Install via git: git clone https://github.com/SillyTavern/SillyTavern && cd SillyTavern && npm install then node server.js . Access at localhost:8000. For persistent installation, use the included start.sh script. SillyTavern uses Node.js and runs on any platform. The companion app (STMP) enables mobile access to your SillyTavern instance via Tailscale or local network. Character Cards and the TavernAI Format Chara...
Read more