SA

SAINEMO reMIX

SainemoGGUF by mradermacherUpdated 2024-11-29
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

SAINEMO reMIX needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 4.8 GB (Q2_K) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

12.2B parameter Llama-based model for roleplay

SAINEMO reMIX is a 12.2B parameter Llama model merged from multiple 12B sources. It supports roleplay and large context handling with a trained context of 1024000 tokens. The model is available in GGUF format for local inference.

Good at

  • Roleplay
  • Large context handling
  • Custom instruction following

Limits

  • No vision support
  • License not specified
  • Large memory requirement for higher quants

Best for

  • Chatbot roleplay scenarios
  • Long‑form content generation
  • Custom instruction following

Who it’s for. Developers building conversational agents and researchers needing a 12B Llama model for local deployment. The model is suitable for applications that require extensive context and roleplay capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.6 GB
Fits Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q3_K_L6.6 GB 8.4 GB
Too big Get file →
IQ4_XS6.8 GB 8.6 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q5_K_S8.5 GB 10.4 GB
Too big Get file →
Q5_K_M8.7 GB 10.6 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 4.79 GB, estimated 6.6 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (7.48 GB, 9.3 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (8.73 GB, 10.6 GB memory) provides higher quality.

What GPU do you need for SAINEMO reMIX?

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: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).

Which SAINEMO reMIX quant should you choose?

Q4_K_M is the usual starting point for SAINEMO reMIX: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.0 GB, about 1.7 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 4.8 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
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilySainemo
Downloads (HF)1,063
Last updated2024-11-29

Frequently asked questions about SAINEMO reMIX

How much VRAM does SAINEMO reMIX need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 SAINEMO reMIX on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SAINEMO reMIX GGUF?

It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.8 GB, Q4_0 is 7.1 GB and 6 more.

What context length does SAINEMO reMIX 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 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download SAINEMO reMIX GGUF?

The files are on Hugging Face in the mradermacher/SAINEMO-reMIX-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run SAINEMO reMIX on 8 GB VRAM?

Yes, with the Q2_K quant it uses about 6.6 GB memory at 8k context.

Does this model support vision?

No, the model does not have vision capabilities.

What is the training context length?

The model was trained on 1024000 tokens.

Other GGUFs of SAINEMO-reMIX

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sainemo models

All Sainemo →

Other medium models

All medium models →