CO

CodeRosa 70B AB1

CoderosaGGUF by altomekUpdated 2024-11-05
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant14.5 GB
Quick answer

CodeRosa 70B AB1 needs about 31.5 GB of memory at IQ3_XS (a 28.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 17 quants, from 14.5 GB (IQ1_S) to 49.4 GB (Q5_K).

CodeRosa 70B AB1 is a 69B-parameter Coderosa model in GGUF format, quantized by altomek. Its trained context length is 4K tokens. The repository has 17 quant files, from 14.5 GB (IQ1_S) to 49.4 GB (Q5_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.5 GB 16.4 GB
Too big Get file →
IQ1_M15.9 GB 17.8 GB
Too big Get file →
IQ2_XXS18.3 GB 20.1 GB
Too big Get file →
IQ2_XS20.3 GB 22.2 GB
Too big Get file →
IQ2_S21.4 GB 23.2 GB
Too big Get file →
IQ2_M23.2 GB 25.1 GB
Too big Get file →
Q2_K26.2 GB 28.1 GB
Too big Get file →
IQ3_XXS26.6 GB 28.4 GB
Too big Get file →
IQ3_XS28.3 GB 30.2 GB
Too big Get file →
IQ3_S29.9 GB 31.8 GB
Too big Get file →
IQ3_M30.9 GB 32.8 GB
Too big Get file →
Q3_K34.0 GB 35.8 GB
Too big Get file →
IQ4_XS36.8 GB 38.7 GB
Too big Get file →
IQ4_NL39.0 GB 40.8 GB
Too big Get file →
Q4_K42.1 GB 44.0 GB
Too big Get file →
Q4_143.2 GB 45.0 GB
Too big Get file →
Q5_K49.4 GB 51.2 GB
Too big Get file →

What GPU do you need for CodeRosa 70B AB1?

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 (20.3 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.3 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_1 (43.2 GB file, about 46.4 GB in use).

Which CodeRosa 70B AB1 quant should you choose?

IQ3_XS (28.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 14.5 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

Architecturellama
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byaltomek
FamilyCoderosa
Licensellama2
Downloads (HF)343
Last updated2024-11-05

Frequently asked questions about CodeRosa 70B AB1

How much VRAM does CodeRosa 70B AB1 need?

About 31.5 GB at IQ3_XS with an 8K context window. That is the 28.3 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 CodeRosa 70B AB1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CodeRosa 70B AB1 GGUF?

It depends on the quant: IQ1_S is 14.5 GB, IQ1_M is 15.9 GB, IQ2_XXS is 18.3 GB, IQ2_XS is 20.3 GB, IQ2_S is 21.4 GB, IQ2_M is 23.2 GB and 11 more.

What context length does CodeRosa 70B AB1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download CodeRosa 70B AB1 GGUF?

The files are on Hugging Face in the altomek/CodeRosa-70B-AB1-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 CodeRosa 70B AB1 use?

Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of CodeRosa-70B-AB1

Similar models

Browse all →

More from altomek

All by altomek →

More Coderosa models

All Coderosa →

Other large models

All large models →