JR

TW3 JRGL v2 i1

JrglGGUF by mradermacherUpdated 2024-12-07
Download on Hugging Face
Parameters72.3B
Context32K
Layers80
Architecturellama
Smallest quant16.2 GB
Quick answer

TW3 JRGL v2 i1 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 20 quants, from 16.2 GB (IQ1_S) to 49.9 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.

TW3 JRGL v2 i1 is a 72.3B-parameter Jrgl model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 20 quant files, from 16.2 GB (IQ1_S) to 49.9 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S16.2 GB 38.2 GB
Too big Get file →
IQ1_M17.6 GB 39.5 GB
Too big Get file →
IQ2_XXS19.8 GB 41.8 GB
Too big Get file →
IQ2_XS21.7 GB 43.7 GB
Too big Get file →
IQ2_S23.4 GB 45.4 GB
Too big Get file →
Q2_K_S24.8 GB 46.8 GB
Too big Get file →
IQ2_M25.2 GB 47.1 GB
Too big Get file →
Q2_K27.1 GB 49.1 GB
Too big Get file →
IQ3_XXS27.7 GB 49.7 GB
Too big Get file →
IQ3_XS29.9 GB 51.9 GB
Too big Get file →
IQ3_S31.6 GB 53.5 GB
Too big Get file →
Q3_K_S31.6 GB 53.5 GB
Too big Get file →
IQ3_M33.3 GB 55.2 GB
Too big Get file →
Q3_K_M35.3 GB 57.3 GB
Too big Get file →
Q3_K_L38.5 GB 60.5 GB
Too big Get file →
IQ4_XS38.8 GB 60.8 GB
Too big Get file →
Q4_041.1 GB 63.1 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 71.9 GB
Too big Get file →

What GPU do you need for TW3 JRGL v2 i1?

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: the best quant that fits is IQ2_M (25.2 GB file, about 47.1 GB in use).

Which TW3 JRGL v2 i1 quant should you choose?

Q4_K_M is the usual starting point for TW3 JRGL v2 i1: it balances file size and quality well. Here it is a 43.8 GB file.

If memory is tight, the smallest file is IQ1_S at 16.2 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
FamilyJrgl
Licenseapache-2.0
Downloads (HF)360
Last updated2024-12-07

Frequently asked questions about TW3 JRGL v2 i1

How much VRAM does TW3 JRGL v2 i1 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 TW3 JRGL v2 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 38.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of TW3 JRGL v2 i1 GGUF?

It depends on the quant: IQ1_S is 16.2 GB, IQ1_M is 17.6 GB, IQ2_XXS is 19.8 GB, IQ2_XS is 21.7 GB, IQ2_S is 23.4 GB, Q2_K_S is 24.8 GB and 14 more.

What context length does TW3 JRGL v2 i1 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 TW3 JRGL v2 i1 GGUF?

The files are on Hugging Face in the mradermacher/TW3-JRGL-v2-i1-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 TW3 JRGL v2 i1 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 TW3-JRGL-v2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Jrgl models

All Jrgl →

Other large models

All large models →