LL

LLaMA 2 7B 32K

LlamaGGUF by rozekUpdated 2023-08-31
Download on Hugging Face
Parameters6.74B
Context32K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

LLaMA 2 7B 32K needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 2.8 GB (Q2_K) to 13.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

LLaMA 2 7B fine‑tuned for 32K context

LLaMA‑2‑7B‑32K is a 6.74B‑parameter model trained for context lengths up to 32,768 tokens. It uses Position Interpolation and Rotary Position Embeddings to enable large‑context inference. The model is available in multiple GGUF quantizations.

Good at

  • Large‑context text generation
  • Fine‑tuned for 32K token windows
  • Supports llama.cpp inference

Limits

  • Requires large RAM for 32K context
  • No vision or multimodal support
  • License is llama2

Best for

  • Long‑form content creation
  • Document summarization with large context
  • Research prototyping with extended context

Who it’s for. Developers and researchers who need a 7B LLaMA model capable of handling up to 32K tokens in llama.cpp. Suitable for applications that require extended context without switching to larger models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 7.6 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q4_14.2 GB 9.0 GB
Too big Get file →
Q5_04.7 GB 9.4 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q5_15.1 GB 9.9 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
F1613.5 GB 18.3 GB
Too big Get file →

For 8‑GB VRAM, use Q4_0 (file size 3.83 GB, estimated 8.6 GB memory). For 12‑GB VRAM, Q6_K (5.53 GB, 10.3 GB memory) or Q8_0 (7.16 GB, 12 GB memory) are suitable. Higher precision quants like F16 require 18.3 GB memory and are best on systems with ≥20 GB RAM.

What GPU do you need for LLaMA 2 7B 32K?

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: the best quant that fits is Q3_K_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which LLaMA 2 7B 32K quant should you choose?

Q4_K_M is the usual starting point for LLaMA 2 7B 32K: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.8 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
Parameters6.74B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized byrozek
FamilyLlama
Licensellama2
Downloads (HF)953
Last updated2023-08-31

Frequently asked questions about LLaMA 2 7B 32K

How much VRAM does LLaMA 2 7B 32K need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 7B 32K on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LLaMA 2 7B 32K GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, Q4_0 is 3.8 GB, Q4_K_S is 3.9 GB and 9 more.

What context length does LLaMA 2 7B 32K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download LLaMA 2 7B 32K GGUF?

The files are on Hugging Face in the rozek/LLaMA-2-7B-32K_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 7B 32K 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.

Can I run LLaMA 2 7B 32K on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantizations, which require about 8.6 GB of memory at 8K context.

Does this model support vision tasks?

No, it is a text‑only model with no vision or multimodal capabilities.

What context size should I use for best performance?

Keep the context as small as possible; the model was fine‑tuned for 32K but large contexts need more RAM.

Similar models

Browse all →

More from rozek

All by rozek →

More Llama models

All Llama →

Other small models

All small models →