TokenAssemble

Runtime comparison

ExLlamaV2 vs MLX LM

ExLlamaV2 is a MIT-licensed runtime for Linux · Windows running on CUDA · ROCm; MLX LM is MIT-licensed for macOS on Metal. MLX LM rates easier to set up (4/5 vs 3/5 in our sourced ratings). Pick ExLlamaV2 for maximum control over how the model runs; pick MLX LM for maximum control over how the model runs.

SpecExLlamaV2MLX LM
LicenseMITMIT
Operating systemsLinux · WindowsmacOS
GPU backendsCUDA · ROCmMetal
Installpip / sourcepip
Ease of use3/54/5
Quant formatsexl2, gptqmlx
Engineexllamav2mlx
GitHub stars4,5816,236
Latest versionv0.3.2v0.31.3
Graphical app (GUI)NoNo
Server modeNoYes
OpenAI-compatible APINoYes
CPU offloadNoNo
Multi-GPUYesNo
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 →

MLX LM

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

Full MLX LM 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); MLX LM github.com/ml-explore/mlx-lm (as of 2026-07-08).