CA

causallm_14b

GGUFGGUF by TheBlokeUpdated 2023-10-23
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architecturellama
Smallest quant8.2 GB
Quick answer

causallm_14b needs about 17.1 GB of memory at Q5_0 (a 9.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 8.2 GB (Q4_0) to 15.1 GB (Q8_0).

CausalLM 14B – 14 billion‑parameter LLaMA‑style model with vision and tool support

CausalLM 14B is a 14 billion‑parameter LLaMA‑based model trained on a 1.3 B‑token curated dataset. It supports 8192‑token context, vision, and tool usage. The model is available in multiple GGUF quantizations for local inference.

Good at

  • Vision and tool integration
  • Large context handling
  • High consistency with 7B and 14B variants

Limits

  • Requires >15 GB VRAM for Q4_0 at 8 k context
  • No official GPU‑only quantization beyond GGUF
  • License is wtfpl – no commercial restrictions

Best for

  • Local chat agents needing vision
  • Fine‑tuning on custom datasets
  • Running on high‑VRAM GPUs

Who it’s for. Users who need a large LLaMA‑style model with vision and tool capabilities for local deployment. Suitable for developers and researchers with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_08.2 GB 15.4 GB
Too big Get file →
Q4_19.0 GB 16.2 GB
Too big Get file →
Q5_09.9 GB 17.1 GB
Too big Get file →
Q5_110.7 GB 17.9 GB
Too big Get file →
Q8_015.1 GB 22.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (8.18 GB file, ~15.4 GB RAM). For 12 GB VRAM, Q4_1 (9.01 GB file, ~16.2 GB RAM). For 16 GB VRAM, Q5_0 (9.85 GB file, ~17.1 GB RAM). Estimates are approximate.

What GPU do you need for causallm_14b?

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: the best quant that fits is Q4_0 (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.1 GB file, about 22.3 GB in use).

Which causallm_14b quant should you choose?

Q5_0 (9.9 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_0 at 8.2 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
Parameters14.2B
Layers40
Trained context8,192 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
Base modelCausalLM/14B
Licensewtfpl
Downloads (HF)4,948
Last updated2023-10-23

Frequently asked questions about causallm_14b

How much VRAM does causallm_14b need?

About 17.1 GB at Q5_0 with an 8K context window. That is the 9.9 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 causallm_14b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of causallm_14b GGUF?

It depends on the quant: Q4_0 is 8.2 GB, Q4_1 is 9.0 GB, Q5_0 is 9.9 GB, Q5_1 is 10.7 GB, Q8_0 is 15.1 GB.

What context length does causallm_14b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.

Where can I download causallm_14b GGUF?

The files are on Hugging Face in the TheBloke/CausalLM-14B-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 causallm_14b use?

Hugging Face lists the license as wtfpl. 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 CausalLM 14B on 8 GB VRAM?

Only with Q4_0 quantization; it requires about 15.4 GB of RAM at 8 k context, so 8 GB VRAM is insufficient for full inference.

Does the model support vision?

Yes, the model has detected vision ability and can process image inputs.

Is the model free to use commercially?

The model is licensed under wtfpl, which allows commercial use without restrictions.

Other GGUFs of 14B

Similar models

Browse all →

More from TheBloke

All by TheBloke →

Other medium models

All medium models →