LL

CodeLlama-3x7B-dialect-experts-it

LlamaGGUF by mradermacherUpdated 2024-06-05
Download on Hugging Face
Parameters15.4B
Context16K
Layers32
Architecturellama
Smallest quant5.7 GB
Quick answer

CodeLlama-3x7B-dialect-experts-it needs about 14.1 GB of memory at Q4_K_M (a 9.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 5.7 GB (Q2_K) to 16.4 GB (Q8_0).

CodeLlama-3x7B-dialect-experts-it is a 15.4B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 14 quant files, from 5.7 GB (Q2_K) to 16.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.7 GB 10.5 GB
Too big Get file →
IQ3_XS6.3 GB 11.1 GB
Too big Get file →
IQ3_S6.7 GB 11.5 GB
Too big Get file →
Q3_K_S6.7 GB 11.5 GB
Too big Get file →
IQ3_M6.9 GB 11.7 GB
Too big Get file →
Q3_K_M7.4 GB 12.2 GB
Too big Get file →
Q3_K_L8.1 GB 12.9 GB
Too big Get file →
IQ4_XS8.3 GB 13.1 GB
Too big Get file →
Q4_K_S8.8 GB 13.6 GB
Too big Get file →
Q4_K_M9.3 GB 14.1 GB
Too big Get file →
Q5_K_S10.6 GB 15.4 GB
Too big Get file →
Q5_K_M10.9 GB 15.7 GB
Too big Get file →
Q6_K12.6 GB 17.4 GB
Too big Get file →
Q8_016.4 GB 21.2 GB
Too big Get file →

What GPU do you need for CodeLlama-3x7B-dialect-experts-it?

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: the best quant that fits is IQ3_M (6.9 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (10.9 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (16.4 GB file, about 21.2 GB in use).

Which CodeLlama-3x7B-dialect-experts-it quant should you choose?

Q4_K_M is the usual starting point for CodeLlama-3x7B-dialect-experts-it: it balances file size and quality well. Here it is a 9.3 GB file.

The Q8_0 file is 16.4 GB, about 1.8 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 Q2_K at 5.7 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
Parameters15.4B (approximate, mixture of experts)
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)143
Last updated2024-06-05

Frequently asked questions about CodeLlama-3x7B-dialect-experts-it

How much VRAM does CodeLlama-3x7B-dialect-experts-it need?

About 14.1 GB at Q4_K_M with an 8K context window. That is the 9.3 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 CodeLlama-3x7B-dialect-experts-it on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CodeLlama-3x7B-dialect-experts-it GGUF?

It depends on the quant: Q2_K is 5.7 GB, IQ3_XS is 6.3 GB, IQ3_S is 6.7 GB, Q3_K_S is 6.7 GB, IQ3_M is 6.9 GB, Q3_K_M is 7.4 GB and 8 more.

What context length does CodeLlama-3x7B-dialect-experts-it support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download CodeLlama-3x7B-dialect-experts-it GGUF?

The files are on Hugging Face in the mradermacher/CodeLlama-3x7B-dialect-experts-it-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →