MI

miqu lzlv

MiquGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant25.8 GB
Quick answer

miqu lzlv needs about 44.9 GB of memory at Q4_K_M (a 41.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 25.8 GB (Q2_K) to 49.1 GB (Q5_K_M).

Miqu LZLV 69B Llama model in GGUF format

Miqu LZLV is a 69B parameter Llama architecture model merged from two source models. It is distributed in GGUF format with multiple quantization options. The model supports a 4096 token context window.

Good at

  • Large context generation
  • High parameter count
  • Merge-based diversity

Limits

  • No official license info
  • Potential gibberish output
  • No vision support

Best for

  • Research on large language models
  • Testing quantization effects
  • Benchmarking llama.cpp

Who it’s for. Researchers and developers interested in large Llama models and quantization experiments. The model is suitable for those who can handle large file sizes and are comfortable with merge-based models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.8 GB 27.6 GB
Too big Get file →
IQ3_XS28.5 GB 30.3 GB
Too big Get file →
IQ3_S30.2 GB 32.1 GB
Too big Get file →
Q3_K_S30.2 GB 32.1 GB
Too big Get file →
IQ3_M31.3 GB 33.1 GB
Too big Get file →
Q3_K_M33.6 GB 35.4 GB
Too big Get file →
Q3_K_L36.5 GB 38.3 GB
Too big Get file →
IQ4_XS37.5 GB 39.3 GB
Too big Get file →
Q4_K_S39.6 GB 41.4 GB
Too big Get file →
Q4_K_M41.7 GB 43.6 GB
Too big Get file →
Q5_K_S47.8 GB 49.6 GB
Too big Get file →
Q5_K_M49.1 GB 50.9 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (25.77 GB, ~29 GB memory at 8k context). For 12‑GB VRAM, Q3_K_S (30.23 GB, ~33.4 GB memory) or IQ3_S (30.23 GB, ~33.4 GB memory). For 16‑GB VRAM, Q4_K_M (41.73 GB, ~44.9 GB memory) or IQ4_XS (37.51 GB, ~40.7 GB memory).

What GPU do you need for miqu lzlv?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.5 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.7 GB file, about 44.9 GB in use).

Which miqu lzlv quant should you choose?

Q4_K_M is the usual starting point for miqu lzlv: it balances file size and quality well. Here it is a 41.7 GB file.

If memory is tight, the smallest file is Q2_K at 25.8 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyMiqu
Base modelycros/miqu-lzlv
Downloads (HF)663
Last updated2024-05-06

Frequently asked questions about miqu lzlv

How much VRAM does miqu lzlv need?

About 44.9 GB at Q4_K_M with an 8K context window. That is the 41.7 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 miqu lzlv on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of miqu lzlv GGUF?

It depends on the quant: Q2_K is 25.8 GB, IQ3_XS is 28.5 GB, IQ3_S is 30.2 GB, Q3_K_S is 30.2 GB, IQ3_M is 31.3 GB, Q3_K_M is 33.6 GB and 6 more.

What context length does miqu lzlv support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download miqu lzlv GGUF?

The files are on Hugging Face in the mradermacher/miqu-lzlv-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?

Use the Q2_K quant, which requires about 29 GB memory at 8k context, so it will not fit on 8 GB VRAM.

Is there a license for this model?

No license information is provided in the supplied data.

Does this model support vision tasks?

The model has no vision support as per the supplied facts.

Other GGUFs of miqu-lzlv

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Miqu models

All Miqu →

Other large models

All large models →