NFS vs SMB for AI Model Storage: Network File System Guide

When your model library grows to hundreds of gigabytes, local storage per machine becomes impractical. Network storage — either NFS or SMB — lets multiple AI workstations share a central model repository. The choice between NFS and SMB affects model load times and inference performance significantly.

Key requirement: Network storage for AI needs 10Gbps Ethernet minimum — 1Gbps (125 MB/s) is a bottleneck for loading 10GB+ models. For complete AI storage and hardware setup guides, LLMHardware.io has network storage recommendations.

NFS vs SMB Performance for LLMs

NFS (Network File System) consistently outperforms SMB for large sequential reads — the pattern of loading model weight files. NFS v4.2 with rsize=1048576 achieves ~85-90% of theoretical network bandwidth. SMB3 on Linux clients achieves ~70-80%. For a 10GbE network, NFS reads a 7B GGUF model (4GB) in ~3-4 seconds vs SMB's ~5-6 seconds. Over a workday, this difference is barely noticeable, but for frequent model switching it adds up.

Caching Strategy

Once a model is loaded into GPU VRAM, network storage speed is irrelevant for inference. The bottleneck is only at model load time. Keep your most-used models in local NVMe storage and use network storage for the archive. Ollama's model cache directory can be set to local NVMe while network storage serves as the download/import location. RAM caching (Linux page cache) keeps recently-accessed models in memory — models accessed within the last hour often load from RAM, not disk.

Practical Setup

Recommended setup: NAS with 10GbE (Synology or QNAP) running NFS v4, mounted on AI workstations. Export options: rw,sync,no_subtree_check,no_root_squash for a trusted local network. Mount with rsize=1048576,wsize=1048576,hard,timeo=600 for optimal performance. ZFS on the NAS provides integrity checking for model files — bit flips in model weights cause subtle inference errors that are difficult to diagnose without file integrity verification.

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