LLM Inference on CPU: When It Makes Sense and How to Optimize

CPU inference for LLMs gets less credit than it deserves. Modern CPUs with AVX-512 support and large L3 caches can run 7B models at 10-20 tokens/second — fast enough for many use cases. For users without dedicated GPUs, or for machines where the GPU is occupied by other tasks, CPU inference is a legitimate option.

When CPU makes sense: Always-on background processing where latency doesn't matter, machines where GPU is doing other work, or any setup where a dedicated AI GPU isn't budget-friendly yet. For GPU upgrade paths when you're ready, see LLMHardware.io's GPU comparison.

CPU Performance Expectations

Performance varies dramatically by CPU. Modern high-core-count desktop chips: Ryzen 9 7950X achieves 15-20 t/s on Llama 3.1 7B Q4_K_M. Intel Core i9-13900K gets 12-15 t/s. Older chips (i7-8700K) manage 4-6 t/s. System RAM bandwidth matters — DDR5 on a 7950X with quad-channel provides ~70 GB/s bandwidth vs DDR4's ~50 GB/s. More cores help (each core handles thread work), but beyond 8-12 active threads there's diminishing returns for llama.cpp's parallelism.

Optimization for CPU Inference

Use Q4_K_M or Q4_K_S quantization — smaller models = less memory bandwidth = faster CPU inference. Set --threads to your physical core count (not hyperthreads — CPU LLM inference doesn't benefit from hyper-threading). Disable --mmap and use --no-mmap to load models fully into RAM — avoids disk I/O during inference. Enable AVX-512 builds of llama.cpp if your CPU supports it (Xeon, some i9/i7) for 20-30% speedup.

Apple Neural Engine

Apple Silicon Macs blur the CPU/GPU boundary. Their Neural Engine (dedicated matrix math hardware) assists inference in addition to the GPU cores. llama.cpp uses Metal to access both the GPU and ANE aspects of Apple's SoC. The result: Apple Silicon CPUs significantly outperform x86 CPUs of similar price for LLM inference — an M4 Mac Mini CPU-only (without GPU offload) matches a mid-range discrete GPU. If your only option is a CPU, any M-series Mac is the best CPU-based AI hardware available.

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