Skip to content
NEWSee what changed →

farbodtavakkoli · gemma4 · based on google/gemma-4-26B-A4B-it

OTel-2.0-Decision-26B-A4B-4bit

OTel-2.0-Decision-26B-A4B-4bit by farbodtavakkoli: a 25.8B-parameter mixture-of-experts open-weight model under the apache-2.0 license and vision.

apache-2.0Mixture of experts262K contextVisionAuto-imported · not yet reviewed

4,194,624 downloads · 9 likes · Model card · synced 2026-11-19

Specifications

Parameters
25.8B
Architecture
moe · gemma4
Layers
30
Hidden size
2,816
KV heads · head dim
8 · 256
Vocabulary
262,144
Native dtype
—
Context window
262,144 tokens
Released
2026-10-06
Last modified on Hub
2026-11-09

Features & licensing

License
apache-2.0
Commercial use
Yes
Modalities
text, vision
Tool / function calling
No
Reasoning mode
No
Languages
EN
Quantised variants on Hub
bitsandbytes
Pipeline
text-generation
safetensorsggufgemma4telecomtelecommunicationsopen-telco-aiclassificationtyped-decisionsdecision-enginesystem-onemixture-of-expertsawqw4a16compressed-tensors4-bitamdrocmnvidiacudah100vllmllama.cpptext-generationconversationalenendpoints_compatibledecision-model

Task fit

Editorial scores (0–100) used by the recommendation engine.

  • Chat70
  • RAG / Q&A70
  • Code70
  • Summarisation70
  • Extraction70
  • Agents70

Hardware to run OTel-2.0-Decision-26B-A4B-4bit

Weights need about 57 GB at FP16, 30 GB at INT8 and 17 GB at INT4. The KV cache adds roughly 246 MB per 1,000 tokens per request. For a reference workload of 5 requests per second with 1,500 input and 300 output tokens, total GPU memory is around 27.9 GB, which fits on 1 × NVIDIA A100 (80 GB).

GPU configurations at the reference workload
ConfigurationVRAMUtilisationEst. first tokenCloud / month
2 × NVIDIA L4 (24 GB)48 GB58 %~0.5 s$1,168
1 × NVIDIA L40S (48 GB)48 GB58 %~0.2 s$1,387
1 × NVIDIA A100 (80 GB)recommended80 GB35 %~0.1 s$2,336
1 × NVIDIA H100 (80 GB)80 GB35 %~0.0 s$3,285

Estimates only. Run an assessment for your own traffic.

Auto-imported from Hugging Face. Architecture, license and feature data are synced from the model repository; the task-fit scores below are provisional defaults until a curator reviews them.

Updates

  • 2026-11-09 · OTel-2.0-Decision-26B-A4B-4bit updated on Hugging Face
  • 2026-11-03 · OTel-2.0-Decision-26B-A4B-4bit updated on Hugging Face