SJ

SJT Moe2x7.5B i1

SjtGGUF by mradermacherUpdated 2025-02-03
Download on Hugging Face
Parameters13.4B
Context32K
Layers28
Architecturellama
Smallest quant3.0 GB
Quick answer

SJT Moe2x7.5B i1 needs about 9.6 GB of memory at Q4_K_M (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 3.0 GB (IQ1_S) to 11.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

SJT Moe2x7.5B i1 is a 13.4B-parameter Sjt model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 24 quant files, from 3.0 GB (IQ1_S) to 11.0 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.0 GB 4.4 GB
Fits Get file →
IQ1_M3.2 GB 4.7 GB
Fits Get file →
IQ2_XXS3.7 GB 5.1 GB
Fits Get file →
IQ2_XS4.1 GB 5.5 GB
Fits Get file →
IQ2_S4.2 GB 5.6 GB
Fits Get file →
IQ2_M4.6 GB 6.0 GB
Fits Get file →
Q2_K_S4.7 GB 6.1 GB
Fits Get file →
Q2_K5.0 GB 6.5 GB
Fits Get file →
IQ3_XXS5.3 GB 6.7 GB
Fits Get file →
IQ3_XS5.6 GB 7.1 GB
Fits Get file →
IQ3_S5.9 GB 7.4 GB
Tight Get file →
Q3_K_S5.9 GB 7.4 GB
Tight Get file →
IQ3_M6.0 GB 7.5 GB
Tight Get file →
Q3_K_M6.5 GB 8.0 GB
Tight Get file →
Q3_K_L7.0 GB 8.5 GB
Too big Get file →
IQ4_XS7.2 GB 8.7 GB
Too big Get file →
IQ4_NL7.6 GB 9.1 GB
Too big Get file →
Q4_07.7 GB 9.1 GB
Too big Get file →
Q4_K_S7.7 GB 9.1 GB
Too big Get file →
Q4_K_M8.2 GB 9.6 GB
Too big Get file →
Q4_18.5 GB 9.9 GB
Too big Get file →
Q5_K_S9.3 GB 10.7 GB
Too big Get file →
Q5_K_M9.5 GB 11.0 GB
Too big Get file →
Q6_K11.0 GB 12.4 GB
Too big Get file →

What GPU do you need for SJT Moe2x7.5B 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: the best quant that fits is IQ2_M (4.6 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.5 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.0 GB file, about 12.4 GB in use).

Which SJT Moe2x7.5B i1 quant should you choose?

Q4_K_M is the usual starting point for SJT Moe2x7.5B i1: it balances file size and quality well. Here it is a 8.2 GB file.

If memory is tight, the smallest file is IQ1_S at 3.0 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
Parameters13.4B (approximate, mixture of experts)
Layers28
Trained context32,768 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilySjt
Licenseapache-2.0
Downloads (HF)15
Last updated2025-02-03

Frequently asked questions about SJT Moe2x7.5B i1

How much VRAM does SJT Moe2x7.5B i1 need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 8.2 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 SJT Moe2x7.5B i1 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SJT Moe2x7.5B i1 GGUF?

It depends on the quant: IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.7 GB, IQ2_XS is 4.1 GB, IQ2_S is 4.2 GB, IQ2_M is 4.6 GB and 18 more.

What context length does SJT Moe2x7.5B i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download SJT Moe2x7.5B i1 GGUF?

The files are on Hugging Face in the mradermacher/SJT-Moe2x7.5B-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 SJT Moe2x7.5B 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.

Other GGUFs of SJT-Moe2x7.5B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sjt models

All Sjt →

Other medium models

All medium models →