LL

Llama 2 34b Uncode

LlamaGGUF by RichardErkhovUpdated 2024-09-02
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant2.9 GB
Quick answer

Llama 2 34b Uncode needs about 22.3 GB of memory at Q4_K_M (a 20.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 2.9 GB (IQ4_NL) to 25.3 GB (Q5_1).

Llama 2 34b Uncode is a 33.7B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 16K tokens. The repository has 20 quant files, from 2.9 GB (IQ4_NL) to 25.3 GB (Q5_1).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL2.9 GB 5.0 GB
Fits Get file →
Q4_K_S5.9 GB 8.0 GB
Too big Get file →
Q2_K12.5 GB 14.6 GB
Too big Get file →
IQ3_XS13.9 GB 16.0 GB
Too big Get file →
Q3_K_S14.6 GB 16.7 GB
Too big Get file →
IQ3_S14.7 GB 16.8 GB
Too big Get file →
IQ3_M15.2 GB 17.3 GB
Too big Get file →
Q3_K16.3 GB 18.4 GB
Too big Get file →
Q3_K_M16.3 GB 18.4 GB
Too big Get file →
Q3_K_L17.8 GB 19.9 GB
Too big Get file →
IQ4_XS18.2 GB 20.3 GB
Too big Get file →
Q5_018.3 GB 20.4 GB
Too big Get file →
Q5_K_M18.4 GB 20.5 GB
Too big Get file →
Q4_019.1 GB 21.2 GB
Too big Get file →
Q4_K20.2 GB 22.3 GB
Too big Get file →
Q4_K_M20.2 GB 22.3 GB
Too big Get file →
Q4_121.1 GB 23.3 GB
Too big Get file →
Q5_K_S23.2 GB 25.3 GB
Too big Get file →
Q5_K23.8 GB 25.9 GB
Too big Get file →
Q5_125.3 GB 27.4 GB
Too big Get file →

What GPU do you need for Llama 2 34b Uncode?

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: the best quant that fits is IQ4_NL (2.9 GB file, about 5.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (5.9 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_S (5.9 GB file, about 8.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (13.9 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (21.1 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_1 (25.3 GB file, about 27.4 GB in use).

Which Llama 2 34b Uncode quant should you choose?

Q4_K_M is the usual starting point for Llama 2 34b Uncode: it balances file size and quality well. Here it is a 20.2 GB file.

If memory is tight, the smallest file is IQ4_NL at 2.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters33.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byRichardErkhov
FamilyLlama
Licensellama2
Downloads (HF)29
Last updated2024-09-02

Frequently asked questions about Llama 2 34b Uncode

How much VRAM does Llama 2 34b Uncode need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 20.2 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 Llama 2 34b Uncode on an 8 GB GPU?

Yes, with Q4_K_S: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 2 34b Uncode GGUF?

It depends on the quant: IQ4_NL is 2.9 GB, Q4_K_S is 5.9 GB, Q2_K is 12.5 GB, IQ3_XS is 13.9 GB, Q3_K_S is 14.6 GB, IQ3_S is 14.7 GB and 14 more.

What context length does Llama 2 34b Uncode support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download Llama 2 34b Uncode GGUF?

The files are on Hugging Face in the RichardErkhov/chargoddard_-_llama-2-34b-uncode-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 Llama 2 34b Uncode 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.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other medium models

All medium models →