LL

models--mergekit-community--Llama3-12B-wwe

LlamaGGUF by MaziyarPanahiUpdated 2024-06-16
Download on Hugging Face
Parameters13.7B
Context8K
Layers58
Architecturellama
Smallest quant5.3 GB
Quick answer

models--mergekit-community--Llama3-12B-wwe needs about 10.8 GB of memory at Q4_K_M (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 10 quants, from 5.3 GB (Q2_K) to 14.6 GB (Q8_0).

Llama3‑12B‑wwe GGUF model for local inference

Llama3‑12B‑wwe is a 13.7‑billion‑parameter Llama model fine‑tuned for instruction following. It supports a 8192‑token context window and tool usage. The model is available in multiple GGUF quantizations for llama.cpp compatibility.

Good at

  • Instruction following
  • Tool usage
  • Large context handling

Limits

  • No vision support
  • License not specified
  • Requires 8‑k context for memory estimates

Best for

  • Chatbots on local GPUs
  • Instruction‑driven applications
  • Tool‑enabled workflows

Who it’s for. Developers and researchers who need a Chinese‑instruct Llama model for local deployment. The model is suitable for building chat interfaces or automation tools that rely on tool invocation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.3 GB 7.7 GB
Tight Get file →
Q3_K_S6.1 GB 8.5 GB
Too big Get file →
Q3_K_M6.7 GB 9.2 GB
Too big Get file →
Q3_K_L7.3 GB 9.7 GB
Too big Get file →
Q4_K_S7.9 GB 10.4 GB
Too big Get file →
Q4_K_M8.3 GB 10.8 GB
Too big Get file →
Q5_K_S9.5 GB 11.9 GB
Too big Get file →
Q5_K_M9.7 GB 12.2 GB
Too big Get file →
Q6_K11.2 GB 13.7 GB
Too big Get file →
Q8_014.6 GB 17.0 GB
Too big Get file →

For 8‑GB VRAM use Q4_K_S (file size 7.91 GB, estimated 10.4 GB memory). For 12‑GB VRAM use Q5_K_M (file size 9.74 GB, estimated 12.2 GB memory). For 16‑GB VRAM use Q6_K (file size 11.25 GB, estimated 13.7 GB memory).

What GPU do you need for models--mergekit-community--Llama3-12B-wwe?

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 Q2_K (5.3 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (9.5 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.2 GB file, about 13.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.6 GB file, about 17.0 GB in use).

Which models--mergekit-community--Llama3-12B-wwe quant should you choose?

Q4_K_M is the usual starting point for models--mergekit-community--Llama3-12B-wwe: it balances file size and quality well. Here it is a 8.3 GB file.

The Q8_0 file is 14.6 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 5.3 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
Parameters13.7B
Layers58
Trained context8,192 tokens
KV cache (fp16)232 KB per token

Source

Quantized byMaziyarPanahi
FamilyLlama
Downloads (HF)3,146
Last updated2024-06-16

Frequently asked questions about models--mergekit-community--Llama3-12B-wwe

How much VRAM does models--mergekit-community--Llama3-12B-wwe need?

About 10.8 GB at Q4_K_M with an 8K context window. That is the 8.3 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 models--mergekit-community--Llama3-12B-wwe on an 8 GB GPU?

Yes, with Q2_K: the 5.3 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 models--mergekit-community--Llama3-12B-wwe GGUF?

It depends on the quant: Q2_K is 5.3 GB, Q3_K_S is 6.1 GB, Q3_K_M is 6.7 GB, Q3_K_L is 7.3 GB, Q4_K_S is 7.9 GB, Q4_K_M is 8.3 GB and 4 more.

What context length does models--mergekit-community--Llama3-12B-wwe support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.9 GB at 8K and 1.9 GB at 8K.

Where can I download models--mergekit-community--Llama3-12B-wwe GGUF?

The files are on Hugging Face in the MaziyarPanahi/Llama3-12B-wwe-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, using the Q4_K_S quantization which requires about 10.4 GB of VRAM at 8‑k context.

Does this model support vision tasks?

No, the model has no vision capability.

What context length does it support?

It supports a 8192‑token context window.

Other GGUFs of llama-3-chinese-8b-instruct-v2

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other medium models

All medium models →