TI

TimeCrystal l2 13B i1

TimecrystalGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant3.1 GB
Quick answer

TimeCrystal l2 13B i1 needs about 15.3 GB of memory at Q4_K_M (a 8.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 22 quants, from 3.1 GB (IQ1_S) to 10.9 GB (Q6_K).

TimeCrystal l2 13B i1 – a 13B llama model focused on logic, instruction, and vivid prose

TimeCrystal l2 13B i1 is a 13B parameter llama model that emphasizes logic and instruction following while enhancing prose vividness. It is derived from TimeCrystal-l2-13B and incorporates weighted/imatrix quants. The model supports a 4096 token context window and is released under the apache-2.0 license.

Good at

  • Logic and instruction following
  • Vivid prose generation
  • Roleplay capabilities

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache-2.0

Best for

  • Writing detailed narratives
  • Assisting with instruction-based tasks
  • Roleplaying scenarios

Who it’s for. Developers and researchers who need a balanced model for logic, instruction, and creative writing. The model is suitable for local deployment with GGUF and llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.1 GB 7.0 GB
Fits Get file →
IQ1_M3.4 GB 7.2 GB
Tight Get file →
IQ2_XXS3.8 GB 7.6 GB
Tight Get file →
IQ2_XS4.1 GB 8.0 GB
Tight Get file →
IQ2_S4.4 GB 8.3 GB
Too big Get file →
IQ2_M4.7 GB 8.6 GB
Too big Get file →
Q2_K5.0 GB 8.9 GB
Too big Get file →
IQ3_XXS5.2 GB 9.0 GB
Too big Get file →
IQ3_XS5.6 GB 9.4 GB
Too big Get file →
IQ3_S5.9 GB 9.7 GB
Too big Get file →
Q3_K_S5.9 GB 9.7 GB
Too big Get file →
IQ3_M6.2 GB 10.0 GB
Too big Get file →
Q3_K_M6.5 GB 10.4 GB
Too big Get file →
Q3_K_L7.1 GB 11.0 GB
Too big Get file →
IQ4_XS7.2 GB 11.0 GB
Too big Get file →
IQ4_NL7.6 GB 11.4 GB
Too big Get file →
Q4_07.6 GB 11.4 GB
Too big Get file →
Q4_K_S7.6 GB 11.5 GB
Too big Get file →
Q4_K_M8.1 GB 11.9 GB
Too big Get file →
Q5_K_S9.2 GB 13.0 GB
Too big Get file →
Q5_K_M9.4 GB 13.3 GB
Too big Get file →
Q6_K10.9 GB 14.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (3.11 GB file, 10.3 GB memory). If 12 GB VRAM is available, IQ3_S (5.85 GB file, 13.1 GB memory) offers a good balance. For larger budgets, Q5_K_M (9.42 GB file, 16.6 GB memory) provides higher quality.

What GPU do you need for TimeCrystal l2 13B 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: the best quant that fits is IQ2_M (4.7 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (8.1 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (10.9 GB file, about 18.1 GB in use).

Which TimeCrystal l2 13B i1 quant should you choose?

Q4_K_M is the usual starting point for TimeCrystal l2 13B i1: it balances file size and quality well. Here it is a 8.1 GB file.

If memory is tight, the smallest file is IQ1_S at 3.1 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
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)4,159
Last updated2024-05-06

Frequently asked questions about TimeCrystal l2 13B i1

How much VRAM does TimeCrystal l2 13B i1 need?

About 15.3 GB at Q4_K_M with an 8K context window. That is the 8.1 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 TimeCrystal l2 13B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of TimeCrystal l2 13B i1 GGUF?

It depends on the quant: IQ1_S is 3.1 GB, IQ1_M is 3.4 GB, IQ2_XXS is 3.8 GB, IQ2_XS is 4.1 GB, IQ2_S is 4.4 GB, IQ2_M is 4.7 GB and 16 more.

What context length does TimeCrystal l2 13B i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download TimeCrystal l2 13B i1 GGUF?

The files are on Hugging Face in the mradermacher/TimeCrystal-l2-13B-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 TimeCrystal l2 13B 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.

Can I run TimeCrystal l2 13B i1 on 8 GB VRAM?

Yes, using the IQ1_S quant which requires approximately 10.3 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of TimeCrystal-l2-13B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Timecrystal models

All Timecrystal →

Other medium models

All medium models →