command-a-plus-05-2026-bf16
CohereLabs/command-a-plus-05-2026-bf16
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Command A · General · Command A+ 05-2026
Command A+ 05-2026 is a current General release in the Command A family, certified from its immutable official source revision.
Command A+ 05-2026 is an official self-hostable Cohere release in the Command A General track. It uses Cohere2VisionForConditionalGeneration, carries 218B / 25B MoE, supports a verified context window of 131,072 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Command A+ 05-2026 uses Cohere2VisionForConditionalGeneration with 218B / 25B MoE. The stored architecture profile records 32 layers, hidden width 4096, 128 attention heads and a 131,072 token context ceiling where the official configuration publishes those fields.
Only exact, source-certified variants attached to this release are shown.
CohereLabs/command-a-plus-05-2026-bf16
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
CohereLabs/command-a-plus-05-2026-fp8
Official · FP8 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| FP8 | safetensors | 8 | Official | Runtime certified |
CohereLabs/command-a-plus-05-2026-w4a4
Official · W4A4 · safetensors
Runtime certified: vLLM SGLang Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| W4A4 | safetensors | 4 | Official | Runtime certified |
Use only the listed transformers, vllm, sglang runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
No current FusionPointAI inventory passes every runtime, architecture, topology and memory gate for this exact checkpoint. Use the estimator for global compatible hardware.
The full 218B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
Command A+ 05-2026 is published under apache-2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
command-a-plus-05-2026-fp8, command-a-plus-05-2026-w4a4
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Certified upstream runtime evidence is available for transformers, vllm, sglang.
The stored commercial classification is Commercial Use Allowed. Consult the official apache-2.0 terms for the final obligations.
Last verified: 2026-09-03