Engines
Browse all 40 engines, A to Z. Filter them by chip, licence or what they do better. Listed and community engines explains what the Listed mark needs.

Speeds up decoding in llama.cpp on AMD GPUs.
Fork of ggml-org/llama.cpp
Speeds up prompt processing in Strata on NVIDIA GPUs.
Fork of Niko1221/Strata
Speeds up Qwen 3.8 Flash-Next decoding on AMD Strix Halo with MTP, in a llama.cpp fork.
Fork of ggml-org/llama.cpp
Runs Qwen 3.8 27B with AXQ quantization and MTP on MLX for Apple M5.

Runs DFlash speculative decoding on MLX for Apple M5.

Decodes faster and starts answering sooner on Apple Silicon, using an MTP drafter.

Runs large models such as DeepSeek V4 Flash and GLM 5.3 Flash on Apple Silicon, NVIDIA and AMD.

Loads GGUF models in pure Rust, with quantized Metal kernels and lossless speculative decoding.

Changes how llama.cpp places its cache on NVIDIA GPUs, and decodes Qwen3.6 35B faster than stock.
Fork of ggml-org/llama.cpp
Speeds up GLM-5.3-Flash on Apple M3 in a ds4 fork.
Fork of antirez/ds4
Runs Qwen3.6-35B-A3B 4-bit on Apple M5 with faster decoding and prompt reading.

Adds an expert cache with GPU and RAM tiers to llama.cpp on NVIDIA GPUs.
Fork of ggml-org/llama.cpp
Serves as the reference upstream and runs on Apple Silicon, NVIDIA, AMD, Intel and CPU.

Streams the KV cache between host RAM and VRAM in a llama.cpp fork for NVIDIA GPUs.
Fork of ggml-org/llama.cpp
Speeds up prompt reading in llama.cpp on AMD Strix Halo, using adaptive speculative decoding.
Fork of ggml-org/llama.cpp
Keeps MoE experts in a VRAM-resident cache in a llama.cpp fork for NVIDIA GPUs.
Fork of ggml-org/llama.cpp
Serves many requests at the same time on Apple M2 with higher total throughput.

Runs models in Rust with ISQ and UQFF quantization on Apple Silicon and NVIDIA GPUs.

Serves as the reference upstream for Apple Silicon, built on MLX.

Decodes Qwen3-30B-A3B faster than mlx-lm on an M5 Max.

Runs on Apple Silicon and is the upstream of the MTPLX M1-family build.

Speeds up MTPLX decoding on M1-family Macs.
Fork of youssofal/MTPLX
Streams experts from SSD or RAM into GPU passes, which speeds up prompt processing in llama.cpp on NVIDIA GPUs.
Fork of ggml-org/llama.cpp
Adds batch prefill for GLM models to ds4 on NVIDIA GPUs.
Fork of antirez/ds4
Serves as the reference upstream: a UX wrapper with a model library.

Speeds up prompt reading on Apple Silicon by pairing a second Mac.

Runs Splash on M1 and M2 Macs, where the upstream needs an M3 or newer.
Fork of incoai/splash
Offloads work to Core ML on Apple Silicon and to the XDNA NPU on AMD, in a llama.cpp fork.
Fork of ggml-org/llama.cpp
Builds on mlx-lm to decode Qwen3.5-9B faster than oMLX on Apple Silicon.
Built on ml-explore/mlx-lm
Decodes Qwen2.5-0.5B faster than llama.cpp on AMD GPUs.

Shrinks Qwen3.8-27B with the ROCmFPX format and decodes it faster, in a llama.cpp fork for AMD GPUs.
Fork of ggml-org/llama.cpp
Adds a trellis-coded 3-bit KV cache codec to llama.cpp for NVIDIA and AMD GPUs.
Fork of ggml-org/llama.cpp
Decodes Qwen3.8-27B and Qwen3.6-35B-A3B faster than llama.cpp on Apple M3 and newer.

Speeds up decoding in llama.cpp on AMD GPUs with RDNA patches and a speculative-decoding clamp.
Fork of ggml-org/llama.cpp
Serves as the reference upstream for Strata forks on NVIDIA, AMD and Apple Silicon.

Streams experts from the SSD to cut GPU memory use on Apple Silicon Macs.

Stores MoE experts in RAM tiers for models running on NVIDIA GPUs.

Adds TQ3 weight formats to llama.cpp and an FP4 prompt path on Blackwell GPUs.
Fork of ggml-org/llama.cpp
Serves as the reference upstream for NVIDIA, AMD and Intel GPUs and CPU.

Cuts memory use on Apple Silicon by loading only some of each MoE model's experts.