CO

Command A Plus 05 2026

CommandGGUF by bartowskiUpdated 2026-06-15
Download on Hugging Face
Parameters218B
Context195K
Layers32
Architecturecohere2moe
Smallest quant0.2 GB
Quick answer

Command A Plus 05 2026 needs about 136.7 GB of memory at Q4_K_M (a 135.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 0.2 GB to 232.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Command A Plus 05 2026 – 218B total parameters, 25B active, 128K context

Command A Plus 05 2026 is a decoder‑only Sparse Mixture‑of‑Experts transformer. It contains 218B total parameters with 25B active and supports 128K input context. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Sparse MoE efficiency
  • Enterprise‑grade reasoning

Limits

  • No vision support in GGUF
  • Requires 8K context for memory estimates
  • Large memory footprint for full precision

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Enterprise chatbots

Who it’s for. Developers building enterprise‑grade LLM applications that need large context and efficient inference. The model is suitable for teams that can manage the memory requirements of the various quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.8 GB
Fits Get file →
IQ1_S49.3 GB 50.8 GB
Too big Get file →
IQ1_M54.3 GB (2 parts) 55.9 GB
Too big Get file →
IQ2_XXS62.3 GB (2 parts) 63.8 GB
Too big Get file →
IQ2_XS68.7 GB (2 parts) 70.3 GB
Too big Get file →
IQ2_S69.9 GB (2 parts) 71.5 GB
Too big Get file →
IQ2_M76.6 GB (2 parts) 78.2 GB
Too big Get file →
Q2_K80.1 GB (3 parts) 81.6 GB
Too big Get file →
Q2_K_L80.3 GB (3 parts) 81.9 GB
Too big Get file →
IQ3_XXS93.9 GB (3 parts) 95.5 GB
Too big Get file →
Q3_K_S98.0 GB (3 parts) 99.6 GB
Too big Get file →
IQ3_XS102.2 GB (3 parts) 103.7 GB
Too big Get file →
Q3_K_M102.6 GB (3 parts) 104.2 GB
Too big Get file →
Q3_K_L106.6 GB (3 parts) 108.2 GB
Too big Get file →
IQ3_M106.7 GB (3 parts) 108.3 GB
Too big Get file →
Q3_K_XL106.8 GB (3 parts) 108.4 GB
Too big Get file →
IQ4_XS118.8 GB (4 parts) 120.4 GB
Too big Get file →
IQ4_NL125.4 GB (4 parts) 127.0 GB
Too big Get file →
Q4_0126.1 GB (4 parts) 127.6 GB
Too big Get file →
Q4_K_S129.8 GB (4 parts) 131.4 GB
Too big Get file →
Q4_K_M135.1 GB (4 parts) 136.7 GB
Too big Get file →
Q4_K_L135.4 GB (4 parts) 136.9 GB
Too big Get file →
Q4_1138.8 GB (4 parts) 140.4 GB
Too big Get file →
Q5_K_S152.1 GB (4 parts) 153.7 GB
Too big Get file →
Q5_K_M157.8 GB (5 parts) 159.3 GB
Too big Get file →
Q6_K189.8 GB (5 parts) 191.4 GB
Too big Get file →
Q8_0232.0 GB (6 parts) 233.5 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (49.25 GB file, 50.8 GB memory at 8K context). For 16‑GB VRAM, IQ2_M (54.32 GB file, 55.9 GB memory) or Q2_K (80.06 GB file, 81.6 GB memory). For 24‑GB VRAM, Q4_K_M (135.09 GB file, 136.7 GB memory) or Q5_K_M (157.77 GB file, 159.3 GB memory).

What GPU do you need for Command A Plus 05 2026?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).

Which Command A Plus 05 2026 quant should you choose?

Q4_K_M is the usual starting point for Command A Plus 05 2026: it balances file size and quality well. Here it is a 135.1 GB file.

The Q8_0 file is 232.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecohere2moe
Parameters218B (approximate, mixture of experts)
Layers32
Trained context200,000 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybartowski
FamilyCommand
Licenseapache-2.0
Downloads (HF)3,147
Last updated2026-06-15

Frequently asked questions about Command A Plus 05 2026

How much VRAM does Command A Plus 05 2026 need?

About 136.7 GB at Q4_K_M with an 8K context window. That is the 135.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Command A Plus 05 2026 on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Command A Plus 05 2026 GGUF?

It depends on the quant: file is 0.2 GB, IQ1_S is 49.3 GB, IQ1_M is 54.3 GB, IQ2_XXS is 62.3 GB, IQ2_XS is 68.7 GB, IQ2_S is 69.9 GB and 21 more.

What context length does Command A Plus 05 2026 support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Command A Plus 05 2026 GGUF?

The files are on Hugging Face in the bartowski/command-a-plus-05-2026-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Command A Plus 05 2026 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Command A Plus 05 2026 on 8 GB VRAM?

Use the IQ1_S quantization. It has a file size of 49.25 GB and requires approximately 50.8 GB of VRAM at 8K context, which is beyond 8 GB. Therefore, 8 GB VRAM is insufficient for any quantization of this model.

Does the model support image inputs?

The GGUF version does not support vision inputs. Only text input is supported.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of command-a-plus-05-2026-bf16

Similar models

Browse all →

More from bartowski

All by bartowski →

More Command models

All Command →

Other large models

All large models →