Ternary Bonsai 2 27B

Qwen3.8 family · 27.0B params

2recorded runs

52.5best tok/s

2verified

Evidence: 2 sourced runs · 1 independent source · first recorded Oct 14, 2026. What these labels mean.

What the Ternary Bonsai 2 27B numbers mean

The fastest verified result on our board is 52.5 output tok/s on an M6 Mac mini at 2-bit ternary LUT with a 8192-token context. That is about 19.0 ms per generated token — 500 tokens takes roughly 9.5 seconds.

How much VRAM does Ternary Bonsai 2 27B need?

Ternary Bonsai 2 27B has 27.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Quantisation	Estimated VRAM	Smallest card that fits
Q4_K_M (4-bit)	18.3 GB	24 GB
Q8_0 (8-bit)	33.8 GB	48 GB
FP16 (16-bit)	62.9 GB	80 GB

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Fastest GPUs for this model (best tok/s)

M6 Mac mini52.5

Models with a similar footprint

Model	Params	Q4_K_M weights
gemma-4-26B-A4B-it	27B	15.2 GB
gemma-4-26B-A4B-it-qat	27B	15.2 GB
gemma-4-26B-A4B-it-ultra-uncensored-heretic	27B	15.2 GB
Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP	27B	15.2 GB
Ornstein3.6-27B-MTP-NSC-ACE-SABER	27B	15.2 GB
Qwen3.8-27B-MTP	27B	15.2 GB

Ranked by distance from Ternary Bonsai 2 27B's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
M6 Mac mini	Ternary Bonsai 2 27B	2-bit ternary LUT	anemll forge 6c572a8	8192	52.5 ✓	—	—	src
M6 Mac mini	Ternary Bonsai 2 27B	2-bit ternary LUT	mlx 26.10.1	8192	36.3 ✓	—	—	src