Rankings

Explore benchmarks

Filter by model, hardware, workload and quantization. Every score links to the comparisons and experiments behind it.

Clear filters

Top Engines

Overall needs mobile results; each platform is ranked on its own until then.

Desktop

Top Engines, Desktop, Speed score.
#EngineSpeed score out of 100
1100 /100 Score
299 /100 Score
396 /100 Score
Not ranked in this view
Not rankedMagnitude Magnitude Unsupported
details

Speed Decode speed: tokens generated per second.

Score: 100 is the best result in every comparison an engine entered; 80 is 80% of the best, on average. Only complete experiments with a passed output check count. How rankings work

The score combines counted comparisons. Select one comparison to see its measured values.

† Ollama: approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

† MLX LM: approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype. Its weights are 2-bit in another scheme: mlx-affine-2bit-g128, where most use Q2_0.

† llama.cpp: approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

Magnitude: Unsupported in 2 comparisons. Magnitude 0.2.17 reports this GGUF as Unsupported (magnitude catalog inspect)

Coverage

Speed score per device, out of 100: each device ranked on its own.
Desktop
M5 Max 64 GiB macOS 27 Apple M5 Max
llama.cpp96 out of 100, in 2 of 2 comparisons
MLX LM99 out of 100, in 2 of 2 comparisons
Ollama100 out of 100, in 2 of 2 comparisons
MagnitudeUnsupported Unsupported in 2 comparisons. Magnitude 0.2.17 reports this GGUF as Unsupported (magnitude catalog inspect)

Speed

Speed, Ternary Bonsai 2 27B on M5 Max · 64 GiB, 2-bit · Archive 256 input / 128 output · macOS 27
RankEnginePrefill
1Ollama, approximate comparison, see details Ollama685.8 tok/s
2llama.cpp, approximate comparison, see details ggml-org668.1 tok/s
3MLX LM, approximate comparison, see details Apple (ml-explore)609.2 tok/s
Not rankedMagnitude MagnitudeUnsupported
details

Ternary Bonsai 2 27B on M5 Max · 64 GiB · 2-bit · Archive 256 input / 128 output · macOS 27

Medians with the model warmed; model loading is excluded. Each table uses one matched comparison.

Ollama: † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

MLX LM: † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype. Its weights are 2-bit in another scheme: mlx-affine-2bit-g128, where most use Q2_0.

Magnitude: Magnitude 0.2.17 reports this GGUF as Unsupported (magnitude catalog inspect)

Memory usage by engine

Memory usage by engine, Ternary Bonsai 2 27B on M5 Max · 64 GiB, 2-bit · Archive 256 input / 128 output · macOS 27
RankEngineMemory
1Ollama, approximate comparison, see details Ollama7.94 GiB
2llama.cpp, approximate comparison, see details ggml-org7.94 GiB
3MLX LM, approximate comparison, see details Apple (ml-explore)9.65 GiB
Not rankedMagnitude MagnitudeUnsupported
details

Ternary Bonsai 2 27B on M5 Max · 64 GiB · 2-bit · Archive 256 input / 128 output · macOS 27

Memory ranks require comparable, calibrated measurements. Unavailable measurements remain unranked.

Ollama: † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

llama.cpp: † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype.

MLX LM: † Approximate comparison. The experiments use different effective KV cache precision: f16, model-dtype. Its weights are 2-bit in another scheme: mlx-affine-2bit-g128, where most use Q2_0.

Magnitude: Magnitude 0.2.17 reports this GGUF as Unsupported (magnitude catalog inspect)

Every comparison

Comparisons in this view: each engine's score in each comparison, out of 100, or why it has none.
Comparisonllama.cppMagnitudeMLX LMOllama
Ternary Bonsai 2 27B on M5 Max · 64 GiB 2-bit · Archive 2048 input / 128 output · macOS 27 96, approximateUnsupported97, approximate100, approximate
Ternary Bonsai 2 27B on M5 Max · 64 GiB 2-bit · Archive 256 input / 128 output · macOS 27 95, approximateUnsupported100, approximate100, approximate

Each engine’s Speed score in each matched comparison, out of 100, or why it has none. How rankings work