IN

MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8

InstructGGUF by Theta-LevUpdated 2025-04-04
Download on Hugging Face
Parameters17.4B
Context1000K
Layers59
Architecturellama
Smallest quant12.4 GB
Quick answer

MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8 needs about 14.9 GB of memory at Q5_K_M (a 12.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.9 GB.

MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8 is a 17.4B-parameter Instruct model in GGUF format, quantized by Theta-Lev. Its trained context length is 1000K tokens. The repository has 1 quant file, from 12.4 GB (Q5_K_M) to 12.4 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M12.4 GB 14.9 GB
Too big Get file →

What GPU do you need for MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8?

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: the best quant that fits is Q5_K_M (12.4 GB file, about 14.9 GB in use).

Which MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8 quant should you choose?

Q5_K_M (12.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters17.4B
Layers59
Trained context1,024,000 tokens
KV cache (fp16)236 KB per token

Source

Quantized byTheta-Lev
FamilyInstruct
Downloads (HF)12
Last updated2025-04-04

Frequently asked questions about MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8

How much VRAM does MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8 need?

About 14.9 GB at Q5_K_M with an 8K context window. That is the 12.4 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 MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8 GGUF?

It depends on the quant: Q5_K_M is 12.4 GB.

What context length does MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.0 GB at 8K and 7.9 GB at 32K.

Where can I download MN Instruct 2407 17.5B BRAINSTORM 20x FORM 8 GGUF?

The files are on Hugging Face in the Theta-Lev/MN-Instruct-2407-17.5B-BRAINSTORM-20x-FORM-8-Q5_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Theta-Lev

All by Theta-Lev →

More Instruct models

All Instruct →

Other medium models

All medium models →