CR

cram 2.6b cjke reasoning rl v3

CramGGUF by octopusmegalopodUpdated 2026-06-11
Download on Hugging Face
Parameters2.57B
Context125K
Layers30
Architecturelfm2
Smallest quant1.8 GB
Quick answer

cram 2.6b cjke reasoning rl v3 needs about 4.3 GB of memory at Q5_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.8 GB (Q5_K_M) to 5.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

cram 2.6b cjke reasoning rl v3 is a 2.57B-parameter Cram model in GGUF format, quantized by octopusmegalopod. Its trained context length is 125K tokens. The repository has 2 quant files, from 1.8 GB (Q5_K_M) to 5.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M1.8 GB 4.3 GB
Fits Get file →
BF165.1 GB 7.7 GB
Tight Get file →

What GPU do you need for cram 2.6b cjke reasoning rl v3?

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: the best quant that fits is Q5_K_M (1.8 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.1 GB file, about 7.7 GB in use).

Which cram 2.6b cjke reasoning rl v3 quant should you choose?

Q5_K_M (1.8 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

Architecturelfm2
Parameters2.57B
Layers30
Trained context128,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byoctopusmegalopod
FamilyCram
Downloads (HF)21
Last updated2026-06-11

Frequently asked questions about cram 2.6b cjke reasoning rl v3

How much VRAM does cram 2.6b cjke reasoning rl v3 need?

About 4.3 GB at Q5_K_M with an 8K context window. That is the 1.8 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 cram 2.6b cjke reasoning rl v3 on an 8 GB GPU?

Yes, with BF16: the 5.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cram 2.6b cjke reasoning rl v3 GGUF?

It depends on the quant: Q5_K_M is 1.8 GB, BF16 is 5.1 GB.

What context length does cram 2.6b cjke reasoning rl v3 support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download cram 2.6b cjke reasoning rl v3 GGUF?

The files are on Hugging Face in the octopusmegalopod/cram-2.6b-cjke-reasoning-rl-v3-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 octopusmegalopod

All by octopusmegalopod →

Other tiny models

All tiny models →