CO

commandr

Command RGGUF by DavidAUUpdated 2026-05-21
Download on Hugging Face
Parameters35B
Context128K
Layers40
Architecturecommand-r
Smallest quant9.1 GB
Quick answer

commandr needs about 32.8 GB of memory at Q4_K_M (a 21.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 9.1 GB (IQ1_M) to 28.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 42.9 GB.

Command-R 35B with IMATRIX NEO V1 upgrades

Command-R 35B is a large language model with 35 billion parameters. It supports a context length of 131 072 tokens and is released under the Apache‑2.0 license. The model is optimized for role‑play and instruction following.

Good at

  • Long‑form generation
  • Role‑play scenarios
  • Instruction following

Limits

  • 131 072‑token context only
  • No vision support
  • Requires large VRAM for higher quants

Best for

  • Creative writing with extended context
  • Chatbot development needing role‑play
  • Complex instruction following tasks

Who it’s for. Developers and researchers who need a large, open‑source model for extended dialogue or creative content. The model is suitable for applications that can accommodate its memory requirements and do not need vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M9.1 GB 20.4 GB
Too big Get file →
IQ2_XXS10.2 GB 21.4 GB
Too big Get file →
IQ2_XS11.1 GB 22.3 GB
Too big Get file →
Q2_K13.8 GB 25.1 GB
Too big Get file →
IQ3_XXS13.8 GB 25.1 GB
Too big Get file →
IQ3_XS15.1 GB 26.3 GB
Too big Get file →
IQ3_S15.9 GB 27.1 GB
Too big Get file →
Q3_K_M17.6 GB 28.9 GB
Too big Get file →
IQ4_XS19.2 GB 30.4 GB
Too big Get file →
Q4_K_M21.5 GB 32.8 GB
Too big Get file →
Q5_K_S24.3 GB 35.6 GB
Too big Get file →
Q6_K28.7 GB 39.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (9.15 GB) or IQ2_XXS (10.19 GB). With 12 GB VRAM, IQ2_XS (11.1 GB) or Q2_K (13.82 GB) are suitable. For 16 GB VRAM, Q3_K_M (17.62 GB) or IQ4_XS (19.2 GB) provide better quality. Memory estimates are approximate.

What GPU do you need for commandr?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ2_XS (11.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ4_XS (19.2 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (28.7 GB file, about 39.9 GB in use).

Which commandr quant should you choose?

Q4_K_M is the usual starting point for commandr: it balances file size and quality well. Here it is a 21.5 GB file.

If memory is tight, the smallest file is IQ1_M at 9.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecommand-r
Parameters35B
Layers40
Trained context131,072 tokens
KV cache (fp16)1280 KB per token

Source

Quantized byDavidAU
FamilyCommand R
Licenseapache-2.0
Downloads (HF)2,399
Last updated2026-05-21

Frequently asked questions about commandr

How much VRAM does commandr need?

About 32.8 GB at Q4_K_M with an 8K context window. That is the 21.5 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 commandr on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of commandr GGUF?

It depends on the quant: IQ1_M is 9.1 GB, IQ2_XXS is 10.2 GB, IQ2_XS is 11.1 GB, Q2_K is 13.8 GB, IQ3_XXS is 13.8 GB, IQ3_XS is 15.1 GB and 6 more.

What context length does commandr support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 10.7 GB at 8K and 42.9 GB at 32K.

Where can I download commandr GGUF?

The files are on Hugging Face in the DavidAU/Command-R-01-Ultra-NEO-V1-35B-IMATRIX-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 commandr 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‑R on 8 GB VRAM?

Use the IQ1_M or IQ2_XXS quant, which are under 12 GB file size and require about 20–21 GB VRAM at 8 k context.

Does Command‑R support image input?

No, the model has no vision capability.

Other GGUFs of c4ai-command-r-v01

Similar models

Browse all →

More from DavidAU

All by DavidAU →

More Command R models

All Command R →

Other large models

All large models →