EC

ECE TW3 JRGL V4

EceGGUF by mradermacherUpdated 2024-12-11
Download on Hugging Face
Parameters72.3B
Context32K
Layers80
Architecturellama
Smallest quant27.1 GB
Quick answer

ECE TW3 JRGL V4 needs about 65.7 GB of memory at Q4_K_M (a 43.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 27.1 GB (Q2_K) to 49.9 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.

ECE TW3 JRGL V4 is a 72.3B-parameter Ece model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 8 quant files, from 27.1 GB (Q2_K) to 49.9 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K27.1 GB 49.0 GB
Too big Get file →
Q3_K_S31.6 GB 53.5 GB
Too big Get file →
Q3_K_M35.3 GB 57.2 GB
Too big Get file →
Q3_K_L38.5 GB 60.5 GB
Too big Get file →
IQ4_XS39.1 GB 61.1 GB
Too big Get file →
Q4_K_S41.3 GB 63.3 GB
Too big Get file →
Q4_K_M43.8 GB 65.7 GB
Too big Get file →
Q5_K_S49.9 GB 71.8 GB
Too big Get file →

What GPU do you need for ECE TW3 JRGL V4?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which ECE TW3 JRGL V4 quant should you choose?

Q4_K_M is the usual starting point for ECE TW3 JRGL V4: it balances file size and quality well. Here it is a 43.8 GB file.

If memory is tight, the smallest file is Q2_K at 27.1 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
Parameters72.3B
Layers80
Trained context32,768 tokens
KV cache (fp16)2560 KB per token

Source

Quantized bymradermacher
FamilyEce
Licenseapache-2.0
Downloads (HF)49
Last updated2024-12-11

Frequently asked questions about ECE TW3 JRGL V4

How much VRAM does ECE TW3 JRGL V4 need?

About 65.7 GB at Q4_K_M with an 8K context window. That is the 43.8 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 ECE TW3 JRGL V4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ECE TW3 JRGL V4 GGUF?

It depends on the quant: Q2_K is 27.1 GB, Q3_K_S is 31.6 GB, Q3_K_M is 35.3 GB, Q3_K_L is 38.5 GB, IQ4_XS is 39.1 GB, Q4_K_S is 41.3 GB and 2 more.

What context length does ECE TW3 JRGL V4 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 21.5 GB at 8K and 85.9 GB at 32K.

Where can I download ECE TW3 JRGL V4 GGUF?

The files are on Hugging Face in the mradermacher/ECE-TW3-JRGL-V4-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 ECE TW3 JRGL V4 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of ECE-TW3-JRGL-V4

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ece models

All Ece →

Other large models

All large models →