CO

Computer 10

ComputerGGUF by bartowskiUpdated 2026-09-27
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant0.0 GB
Quick answer

Computer 10 needs about 47.2 GB of memory at Q4_K_M (a 44.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 27 quants, from 0.0 GB to 141.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

71‑Billion‑parameter document model based on Llama 3.1

Computer 10 is a 71 B parameter model derived from Llama 3.1. It is trained on a curated anthology of documents and is designed for document‑level generation, not chat. The model has a distinct personality and does not follow a chat template.

Good at

  • Document‑level text generation
  • Non‑chat conversational style
  • Large context support up to 131 072 tokens

Limits

  • No chat template; requires custom prompt format
  • Large memory footprint for higher‑quality quants
  • No vision or multimodal support

Best for

  • Generating long, structured documents
  • Creating conversational transcripts
  • Research‑style content creation

Who it’s for. Users who need a large, document‑centric language model for non‑chat applications. It is suitable for developers who can format prompts with the required **User:** and **Model C:** tags.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.2 GB
Fits Get file →
IQ1_S19.4 GB 22.6 GB
Too big Get file →
IQ1_M20.6 GB 23.7 GB
Too big Get file →
IQ2_XXS22.5 GB 25.7 GB
Too big Get file →
IQ2_XS24.2 GB 27.4 GB
Too big Get file →
IQ2_S25.4 GB 28.6 GB
Too big Get file →
IQ2_M27.0 GB 30.1 GB
Too big Get file →
Q2_K27.7 GB 30.9 GB
Too big Get file →
IQ3_XXS29.0 GB 32.2 GB
Too big Get file →
IQ3_XS30.6 GB 33.8 GB
Too big Get file →
Q3_K_S32.0 GB 35.1 GB
Too big Get file →
IQ3_M33.0 GB 36.2 GB
Too big Get file →
Q3_K_M35.3 GB 38.5 GB
Too big Get file →
Q3_K_L37.5 GB 40.7 GB
Too big Get file →
IQ4_XS38.8 GB 42.0 GB
Too big Get file →
Q4_040.8 GB 44.0 GB
Too big Get file →
IQ4_NL40.8 GB 44.0 GB
Too big Get file →
Q4_K_S41.0 GB 44.2 GB
Too big Get file →
Q4_K_M44.0 GB 47.2 GB
Too big Get file →
Q4_K_L44.7 GB 47.9 GB
Too big Get file →
Q4_144.8 GB 48.0 GB
Too big Get file →
Q5_K_S49.0 GB 52.2 GB
Too big Get file →
Q5_K_M51.1 GB 54.3 GB
Too big Get file →
Q6_K60.1 GB (2 parts) 63.3 GB
Too big Get file →
Q6_K_L60.6 GB (2 parts) 63.8 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →
BF16141.1 GB (4 parts) 144.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (43.97 GB file, ~47.2 GB memory at 8 k context). For 12 GB VRAM, Q4_K_L (44.75 GB file, ~47.9 GB memory). For 16 GB VRAM, Q5_K_M (51.11 GB file, ~54.3 GB memory). These estimates are approximate.

What GPU do you need for Computer 10?

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 (0.0 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ1_M (20.6 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q2_K (27.7 GB file, about 30.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_1 (44.8 GB file, about 48.0 GB in use).

Which Computer 10 quant should you choose?

Q4_K_M is the usual starting point for Computer 10: it balances file size and quality well. Here it is a 44.0 GB file.

The Q8_0 file is 75.0 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 0.0 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

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bybartowski
FamilyComputer
Licensellama3.1
Downloads (HF)10,140
Last updated2026-09-27

Frequently asked questions about Computer 10

How much VRAM does Computer 10 need?

About 47.2 GB at Q4_K_M with an 8K context window. That is the 44.0 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 Computer 10 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Computer 10 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 19.4 GB, IQ1_M is 20.6 GB, IQ2_XXS is 22.5 GB, IQ2_XS is 24.2 GB, IQ2_S is 25.4 GB and 21 more.

What context length does Computer 10 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Computer 10 GGUF?

The files are on Hugging Face in the bartowski/cosmicoptima_computer-10-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 Computer 10 use?

Hugging Face lists the license as llama3.1. 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 Computer 10 on 8 GB VRAM?

No, the smallest quant requires at least 8 GB VRAM for inference. Use a lower‑quality quant if you have less memory.

Does Computer 10 support vision or multimodal inputs?

No, the model only supports text input and has no vision capabilities.

What prompt format does Computer 10 expect?

The prompt must use **User:** and **Model C:** tags with a blank line between turns, ending at **Model C:** with no trailing space.

Other GGUFs of computer-10

Similar models

Browse all →

More from bartowski

All by bartowski →

More Computer models

All Computer →

Other large models

All large models →