command-a-plus-05-2026-w4a4
Support summary
command-a-plus-05-2026-w4a4 is a checkpoint published by Cohere, built on the Cohere2VisionForConditionalGeneration architecture. vLLM lists its architecture, but not this exact checkpoint.
- Configured context
- 200,000 tokens
- License
- apache-2.0
Hugging Face model card
- Publisher
- Cohere
- Task
- image text to text
- License
- apache-2.0
- Library
- transformers
- Architecture
- Cohere2VisionForConditionalGeneration
- Weight tensor elements
- 218.8B
- Tensor types
- U8, BF16
- Quantization
- compressed-tensors · nvfp4-pack-quantized
- Configured context
- 200,000 tokens
- Languages
- en, ar, bg, bn, ca, cs, da, de, el, es, et, fa, fi, fil, fr, ga, he, hi, hr, hu, id, is, it, ja, ko, lt, lv, ms, mt, nl, no, pa, pl, pt, ro, ru, sk, sl, sr, sv, ta, te, th, tr, uk, ur, vi, zh
- Base models
- CohereLabs/command-a-plus-05-2026
- Weight access
- Public
- Repository created
- 2026-05-18
Publisher deployment guidance
- vLLM>=0.25.0
Publisher requirement for the W4A4 artifact. Response parsing requires cohere_melody>=0.9.0; the hardware table lists 1 B200 or 2 H100. Adapt tensor parallelism to the chosen hardware.
Source: CohereLabs/command-a-plus-05-2026-w4a4 · publisher model cardReviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||