Cactus-Compute / gemma-4-26B-A4B-it

huggingface.co
Total runs: 20
24-hour runs: -1
7-day runs: -1
30-day runs: 1
Model's Last Updated: July 11 2026
text-generation

Introduction of gemma-4-26B-A4B-it

Model Details of gemma-4-26B-A4B-it

gemma-4-26B-A4B-it — Cactus CQ (calibrated)

2-, 3-, and 4-bit quantizations of google/gemma-4-26B-A4B-it in the Cactus .weights format for on-device (ARM) inference.

Method
  • CQ Cactus codebook quantization: per-group Hadamard rotation + (2/3-bit) AWQ-style activation scaling + routing-aware per-expert GPTQ — every MoE expert calibrated with its own routed-token Hessian.
  • Embeddings: CQ4 (orthogonal). Norms / router / biases: FP16.
  • Calibration: ~2M tokens of WildChat + AceCode trajectories generated by the model with thinking enabled.
  • 4-bit uses plain RTN (no GPTQ/AWQ): at 4-bit the activation-scaling/GPTQ calibration is net-harmful (a known high-bit AWQ effect), so RTN is the best-performing 4-bit and keeps quality monotonic with bit-width.
Quality — held-out completion perplexity (56k answer tokens, ±~2 PPL noise)
Variant PPL
bf16 baseline 7.25
2-bit RTN (uncalibrated) 33,827
2-bit calibrated 6.81
3-bit RTN (uncalibrated) 32.56
3-bit calibrated 6.32
4-bit (RTN) 6.00
Files
  • weights/gemma-4-26b-a4b-it-cq2.zip — 2-bit calibrated (~2.36 bits/weight overall)
  • weights/gemma-4-26b-a4b-it-cq3.zip — 3-bit calibrated
  • weights/gemma-4-26b-a4b-it-cq4.zip — 4-bit RTN

Runs on-device via the Cactus runtime (ARM).

Runs of Cactus-Compute gemma-4-26B-A4B-it on huggingface.co

20
Total runs
-1
24-hour runs
0
3-day runs
-1
7-day runs
1
30-day runs

More Information About gemma-4-26B-A4B-it huggingface.co Model

More gemma-4-26B-A4B-it license Visit here:

https://choosealicense.com/licenses/gemma

gemma-4-26B-A4B-it huggingface.co

gemma-4-26B-A4B-it huggingface.co is an AI model on huggingface.co that provides gemma-4-26B-A4B-it's model effect (), which can be used instantly with this Cactus-Compute gemma-4-26B-A4B-it model. huggingface.co supports a free trial of the gemma-4-26B-A4B-it model, and also provides paid use of the gemma-4-26B-A4B-it. Support call gemma-4-26B-A4B-it model through api, including Node.js, Python, http.

Cactus-Compute gemma-4-26B-A4B-it online free

gemma-4-26B-A4B-it huggingface.co is an online trial and call api platform, which integrates gemma-4-26B-A4B-it's modeling effects, including api services, and provides a free online trial of gemma-4-26B-A4B-it, you can try gemma-4-26B-A4B-it online for free by clicking the link below.

Cactus-Compute gemma-4-26B-A4B-it online free url in huggingface.co:

https://huggingface.co/Cactus-Compute/gemma-4-26B-A4B-it

gemma-4-26B-A4B-it install

gemma-4-26B-A4B-it is an open source model from GitHub that offers a free installation service, and any user can find gemma-4-26B-A4B-it on GitHub to install. At the same time, huggingface.co provides the effect of gemma-4-26B-A4B-it install, users can directly use gemma-4-26B-A4B-it installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

gemma-4-26B-A4B-it install url in huggingface.co:

https://huggingface.co/Cactus-Compute/gemma-4-26B-A4B-it

Url of gemma-4-26B-A4B-it

Provider of gemma-4-26B-A4B-it huggingface.co

Cactus-Compute
ORGANIZATIONS

Other API from Cactus-Compute

huggingface.co

Total runs: 134.4K
Run Growth: 109.9K
Growth Rate: 81.83%
Updated:October 19 2026
huggingface.co

Total runs: 43.1K
Run Growth: 43.1K
Growth Rate: 100.00%
Updated:October 19 2026
huggingface.co

Total runs: 2.8K
Run Growth: -35.7K
Growth Rate: -1252.78%
Updated:September 03 2026