LL

Meta-Llama-3-8B-Instruct-imatrix

LlamaGGUF by lmstudio-communityUpdated 2024-05-03
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant3.8 GB
Quick answer

Meta-Llama-3-8B-Instruct-imatrix needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 3.8 GB (IQ3_M) to 8.5 GB (Q8_0).

Meta‑Llama‑3‑8B‑Instruct‑imatrix – 8B instruction‑tuned Llama 3 model in GGUF format

Meta‑Llama‑3‑8B‑Instruct‑imatrix is an 8 billion‑parameter instruction‑tuned Llama 3 model. It is available in multiple GGUF quantizations and supports up to 8 192 context tokens. The model is tuned for following instructions and general usage, including conversation, coding, and world knowledge.

Good at

  • Instruction following
  • General conversation
  • Coding tasks

Limits

  • No vision support
  • Requires 8 192 context tokens for full capability
  • License: llama3

Best for

  • Chatbots with instruction prompts
  • Code generation and debugging
  • General knowledge queries

Who it’s for. Developers and researchers who need a compact, instruction‑tuned Llama 3 model for local deployment. The model is suitable for applications that require fast inference and moderate VRAM usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (≈6.5 GB memory at 8 k context). If 12 GB VRAM is available, Q5_K_M (≈7.3 GB) provides higher quality. For 16 GB+ VRAM, Q6_K (≈8.2 GB) or Q8_0 (≈10.1 GB) can be used for best performance. Memory estimates are approximate.

What GPU do you need for Meta-Llama-3-8B-Instruct-imatrix?

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 IQ3_M (3.8 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).

Which Meta-Llama-3-8B-Instruct-imatrix quant should you choose?

Q4_K_M is the usual starting point for Meta-Llama-3-8B-Instruct-imatrix: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 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 IQ3_M at 3.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bylmstudio-community
FamilyLlama
Licensellama3
Downloads (HF)6,936
Last updated2024-05-03

Frequently asked questions about Meta-Llama-3-8B-Instruct-imatrix

How much VRAM does Meta-Llama-3-8B-Instruct-imatrix need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Meta-Llama-3-8B-Instruct-imatrix on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Meta-Llama-3-8B-Instruct-imatrix GGUF?

It depends on the quant: IQ3_M is 3.8 GB, Q4_K_M is 4.9 GB, Q5_K_M is 5.7 GB, Q6_K is 6.6 GB, Q8_0 is 8.5 GB.

What context length does Meta-Llama-3-8B-Instruct-imatrix support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Meta-Llama-3-8B-Instruct-imatrix GGUF?

The files are on Hugging Face in the lmstudio-community/Meta-Llama-3-8B-Instruct-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 Meta-Llama-3-8B-Instruct-imatrix use?

Hugging Face lists the license as llama3. 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 Meta‑Llama‑3‑8B‑Instruct‑imatrix on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 6.5 GB of VRAM at 8 k context.

Does this model support image input?

No, the model has no vision capabilities.

What context length does it support?

It supports up to 8 192 tokens of context.

Other GGUFs of Meta-Llama-3-8B-Instruct

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Llama models

All Llama →

Other small models

All small models →