TokenAssemble

Runtime comparison

ExLlamaV2 vs LM Studio

ExLlamaV2 is a MIT-licensed runtime for Linux · Windows running on CUDA · ROCm; LM Studio is proprietary-licensed for Linux · macOS · Windows on CUDA · Metal · CPU · Vulkan · ROCm. LM Studio rates easier to set up (5/5 vs 3/5 in our sourced ratings). Pick ExLlamaV2 for maximum control over how the model runs; pick LM Studio for people who want a desktop app and no terminal.

SpecExLlamaV2LM Studio
LicenseMITproprietary
Operating systemsLinux · WindowsLinux · macOS · Windows
GPU backendsCUDA · ROCmCUDA · Metal · CPU · Vulkan · ROCm
Installpip / sourcebinary
Ease of use3/55/5
Quant formatsexl2, gptqgguf, mlx
Engineexllamav2llama.cpp|mlx
GitHub stars4,581
Latest versionv0.3.2
Graphical app (GUI)NoYes
Server modeNoYes
OpenAI-compatible APINoYes
CPU offloadNoYes
Multi-GPUYesYes
Speculative decodingYesNo
LoRA supportYesYes
KV-cache quantizationYesYes

Which should you use?

ExLlamaV2

Best for maximum control over how the model runs. Command line and server, runs on CUDA · ROCm.

Full ExLlamaV2 guide →

LM Studio

Best for people who want a desktop app and no terminal. Ships a graphical app, runs on CUDA · Metal · CPU · Vulkan · ROCm.

Full LM Studio guide →

Neither runtime changes whether a model fits — that is your memory and quantization. Check your hardware first, then pick the runtime.

Sources: ExLlamaV2 github.com/turboderp-org/exllamav2 (as of 2026-07-08); LM Studio lmstudio.ai (as of 2026-07-08).