ST

stockmark 100b

StockmarkGGUF by mmngaUpdated 2024-05-18
Download on Hugging Face
Parameters96.2B
Context4K
Layers88
Architecturellama
Smallest quant20.4 GB
Quick answer

stockmark 100b needs about 38.9 GB of memory at Q2_K (a 35.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 13 quants, from 20.4 GB (IQ1_S) to 46.3 GB (Q3_K_M).

stockmark 100b – a 96.2B parameter llama model in GGUF format

stockmark 100b is a 96.2B parameter llama architecture model released under the MIT license. It supports a 4096 token context window and is available in multiple quantized formats for different memory budgets.

Good at

  • Large context reasoning
  • High capacity language modeling
  • Japanese data support

Limits

  • No vision capabilities
  • Requires large VRAM for full precision
  • No mixture of experts

Best for

  • Research on large language models
  • Fine‑tuning for specialized Japanese tasks
  • Benchmarking quantization effects

Who it’s for. Developers and researchers who need a large llama model with a 4096 token context window and are comfortable working with GGUF files. The model is suitable for those who can allocate sufficient GPU memory or use quantized versions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S20.4 GB 22.3 GB
Too big Get file →
IQ1_M22.3 GB 24.3 GB
Too big Get file →
IQ2_XXS25.6 GB 27.5 GB
Too big Get file →
IQ2_XS28.4 GB 30.4 GB
Too big Get file →
IQ2_S29.9 GB 31.8 GB
Too big Get file →
IQ2_M32.5 GB 34.4 GB
Too big Get file →
Q2_K35.5 GB 37.4 GB
Too big Get file →
IQ3_XXS37.0 GB 39.0 GB
Too big Get file →
IQ3_XS39.4 GB 41.4 GB
Too big Get file →
Q3_K_S41.6 GB 43.5 GB
Too big Get file →
IQ3_S41.7 GB 43.7 GB
Too big Get file →
IQ3_M43.1 GB 45.1 GB
Too big Get file →
Q3_K_M46.3 GB 48.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (20.35 GB file, 23.8 GB memory at 8 k context). For 12 GB VRAM, IQ1_M (22.31 GB file, 25.8 GB memory). For 16 GB VRAM, IQ2_XXS (25.57 GB file, 29 GB memory).

What GPU do you need for stockmark 100b?

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: the best quant that fits is IQ1_S (20.4 GB file, about 23.8 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_XS (28.4 GB file, about 31.9 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_M (43.1 GB file, about 46.6 GB in use).

Which stockmark 100b quant should you choose?

Q2_K (35.5 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is IQ1_S at 20.4 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
Parameters96.2B
Layers88
Trained context4,096 tokens
KV cache (fp16)352 KB per token

Source

Quantized bymmnga
FamilyStockmark
Licensemit
Downloads (HF)1,190
Last updated2024-05-18

Frequently asked questions about stockmark 100b

How much VRAM does stockmark 100b need?

About 38.9 GB at Q2_K with an 8K context window. That is the 35.5 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 stockmark 100b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of stockmark 100b GGUF?

It depends on the quant: IQ1_S is 20.4 GB, IQ1_M is 22.3 GB, IQ2_XXS is 25.6 GB, IQ2_XS is 28.4 GB, IQ2_S is 29.9 GB, IQ2_M is 32.5 GB and 7 more.

What context length does stockmark 100b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.0 GB at 8K and 1.5 GB at 4K.

Where can I download stockmark 100b GGUF?

The files are on Hugging Face in the mmnga/stockmark-100b-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 stockmark 100b use?

Hugging Face lists the license as mit. 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 stockmark 100b on 8 GB VRAM?

Use the IQ1_S quantized file, which requires about 23.8 GB of memory at 8 k context. 8 GB VRAM is insufficient for this model.

Does stockmark 100b support vision tasks?

No, the model does not include vision capabilities.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Stockmark models

All Stockmark →

Other large models

All large models →