ST

Stockmark 2 100B Instruct

StockmarkGGUF by a4lgUpdated 2025-11-10
Download on Hugging Face
Parameters96B
Context32K
Layers86
Architecturellama
Smallest quant35.5 GB
Quick answer

Stockmark 2 100B Instruct needs about 61.0 GB of memory at Q4_K_M (a 57.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 35.5 GB (Q2_K) to 192.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.5 GB.

Stockmark 2 100B Instruct is a 96B-parameter Stockmark model in GGUF format, quantized by a4lg. Its trained context length is 32K tokens. The repository has 13 quant files, from 35.5 GB (Q2_K) to 192.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K35.5 GB 38.9 GB
Too big Get file →
Q3_K_S41.6 GB 45.0 GB
Too big Get file →
Q3_K_M46.3 GB 49.7 GB
Too big Get file →
Q3_K_L50.4 GB (2 parts) 53.8 GB
Too big Get file →
Q4_K_S54.6 GB (2 parts) 58.0 GB
Too big Get file →
Q4_K57.6 GB (2 parts) 61.0 GB
Too big Get file →
Q4_K_M57.6 GB (2 parts) 61.0 GB
Too big Get file →
Q5_K_S66.1 GB (2 parts) 69.5 GB
Too big Get file →
Q5_K67.9 GB (2 parts) 71.3 GB
Too big Get file →
Q5_K_M67.9 GB (2 parts) 71.3 GB
Too big Get file →
Q6_K78.8 GB (2 parts) 82.1 GB
Too big Get file →
Q8_0102.0 GB (3 parts) 105.4 GB
Too big Get file →
BF16192.0 GB (4 parts) 195.4 GB
Too big Get file →

What GPU do you need for Stockmark 2 100B Instruct?

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 Q3_K_S (41.6 GB file, about 45.0 GB in use).

Which Stockmark 2 100B Instruct quant should you choose?

Q4_K_M is the usual starting point for Stockmark 2 100B Instruct: it balances file size and quality well. Here it is a 57.6 GB file.

The Q8_0 file is 102.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 35.5 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
Parameters96B
Layers86
Trained context32,768 tokens
KV cache (fp16)344 KB per token

Source

Quantized bya4lg
FamilyStockmark
Licensemit
Downloads (HF)183
Last updated2025-11-10

Frequently asked questions about Stockmark 2 100B Instruct

How much VRAM does Stockmark 2 100B Instruct need?

About 61.0 GB at Q4_K_M with an 8K context window. That is the 57.6 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 2 100B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 38.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Stockmark 2 100B Instruct GGUF?

It depends on the quant: Q2_K is 35.5 GB, Q3_K_S is 41.6 GB, Q3_K_M is 46.3 GB, Q3_K_L is 50.4 GB, Q4_K_S is 54.6 GB, Q4_K is 57.6 GB and 7 more.

What context length does Stockmark 2 100B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.9 GB at 8K and 11.5 GB at 32K.

Where can I download Stockmark 2 100B Instruct GGUF?

The files are on Hugging Face in the a4lg/Stockmark-2-100B-Instruct-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 2 100B Instruct 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.

Similar models

Browse all →

More from a4lg

All by a4lg →

More Stockmark models

All Stockmark →

Other large models

All large models →