Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP

Gemma family · 27.0B params

1recorded run

58.4best tok/s

1verified

Evidence: 1 sourced run · 1 independent source · first recorded Aug 29, 2026. What these labels mean.

What the Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP numbers mean

The fastest verified result on our board is 58.4 output tok/s on an Intel Arc Pro B70 at Q4_K_M with a 262144-token context. That is about 17.1 ms per generated token — 500 tokens takes roughly 8.6 seconds. Prompt processing on the same record runs at 1333.0 tok/s, so a 2,000-token prompt is read in about 1.5 seconds. Peak VRAM was measured at 23.2 GB.

How much VRAM does Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP need?

Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP 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)

Intel Arc Pro B7058.4

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
Ornstein3.6-27B-MTP-NSC-ACE-SABER	27B	15.2 GB
Qwen3.8-27B-MTP	27B	15.2 GB
Ternary Bonsai 2 27B	27B	15.2 GB

Ranked by distance from Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
Intel Arc Pro B70 · 32 GB	Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP	Q4_K_M	llama.cpp b10621 (c1d0e7a00)	262144	58.4 ✓	1333.0	23.2	src