Explore this comparison’s ranking

Comparison Counted

Which engine runs Ternary Bonsai 2 27B best on M5 Max · 64 GiB?

Device
M5 Max · 64 GiB (Apple silicon Macs)
OS
macOS 27
Model
Ternary Bonsai 2 27B, 27B parameters
Weights
2-bit
Workload
Archive 2048 input / 128 output: 2,048 tokens in, 128 out
Decoding
Greedy, batch 1, context 4,096
Power
Plugged in

Speed: Decode speed: tokens generated per second.

Which engine runs Ternary Bonsai 2 27B best on M5 Max · 64 GiB? Ranked by Speed.
#EngineDecode and First token
1Ollama, an approximate comparison, see details Ollama Decode: 44.6 tok/s 2,672 ms first token
2MLX LM, an approximate comparison, see details Apple (ml-explore) Decode: 43.4 tok/s 3,291 ms first token
3llama.cpp, an approximate comparison, see details ggml-org Decode: 42.7 tok/s 2,814 ms first token
Not ranked in this view
Not rankedMagnitude Magnitude Unsupported Unsupported in 1 comparison. Magnitude 0.2.17 reports this GGUF as Unsupported (magnitude catalog inspect)
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

† 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.

Every experiment

Medians over valid trials, with the lowest and highest beneath. Eligible experiments are complete and passed their output check. The ranking above selects each engine's configuration for this objective when its required metrics are measured.

Every experiment in this comparison
ExperimentRanking eligibilityDecode tok/s, higher is betterFirst token ms, lower is betterMemory GiB, lower is betterPrefill tok/s, higher is betterValid trials
Ollama 0.40.13 · Metal · Q2_0 Eligible, approximately: The experiments use different effective KV cache precision: f16, model-dtype.44.6 range44.2–44.62,672 range2,572–2,9418.12 range8.12–8.12767.8 range697.4–798.16of 6 planned
MLX LM 0.32.2 · Metal · mlx-affine-2bit-g128 Eligible, approximately: 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_0.43.4 range40.4–43.73,291 range2,966–3,48214.45 range14.45–14.46622.5 range588.5–690.96of 6 planned
llama.cpp b12110 · Metal · Q2_0 Eligible, approximately: The experiments use different effective KV cache precision: f16, model-dtype.42.7 range42.2–42.82,814 range2,575–3,0788.12 range8.12–8.12728.1 range665.6–795.86of 6 planned
Magnitude 0.2.17 · Metal · Q2_0 Unsupported Magnitude 0.2.17 reports this GGUF as Unsupported (magnitude catalog inspect)––––0of 6 planned

Every trial, metric by metric

The line runs from an experiment's lowest to its highest valid trial, the dot is the median and each tick is one trial. Every scale starts at zero.

Caveats

  • Publisher cards identify the base model but do not always pin the exact export source checkpoint revision.
  • Engines may differ in quantization scheme, effective KV cache precision, kernels, and activations.

About this comparison

Worked out from its experiments: every experiment here shares the device, the OS major version, the power state, the base model, the quantization class and the workload. Measured under methodology v0.6. Comparison id glenn-m5-max-64gb--macos-27--ternary-bonsai-2-27b--2-bit--archive-2048-128.