BL

Blue Rose Coder 12.3B Instruct i1

BlueGGUF by mradermacherUpdated 2024-12-11
Download on Hugging Face
Parameters12.3B
Context32K
Layers48
Architectureqwen2
Smallest quant2.9 GB
Quick answer

Blue Rose Coder 12.3B Instruct i1 needs about 8.8 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 25 quants, from 2.9 GB (IQ1_S) to 10.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Blue Rose Coder 12.3B Instruct i1 is a 12.3B-parameter Blue model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 25 quant files, from 2.9 GB (IQ1_S) to 10.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 4.2 GB
Fits Get file →
IQ1_M3.1 GB 4.4 GB
Fits Get file →
IQ2_XXS3.5 GB 4.8 GB
Fits Get file →
IQ2_XS3.8 GB 5.1 GB
Fits Get file →
IQ2_S4.0 GB 5.3 GB
Fits Get file →
IQ2_M4.3 GB 5.6 GB
Fits Get file →
Q2_K_S4.4 GB 5.7 GB
Fits Get file →
Q2_K4.7 GB 6.0 GB
Fits Get file →
IQ3_XXS4.9 GB 6.2 GB
Fits Get file →
IQ3_XS5.2 GB 6.6 GB
Fits Get file →
Q3_K_S5.5 GB 6.8 GB
Fits Get file →
IQ3_S5.5 GB 6.8 GB
Fits Get file →
IQ3_M5.6 GB 6.9 GB
Fits Get file →
Q3_K_M6.0 GB 7.4 GB
Tight Get file →
Q3_K_L6.5 GB 7.8 GB
Tight Get file →
IQ4_XS6.7 GB 8.0 GB
Too big Get file →
Q4_07.1 GB 8.4 GB
Too big Get file →
Q4_07.1 GB 8.4 GB
Too big Get file →
Q4_07.1 GB 8.4 GB
Too big Get file →
Q4_07.1 GB 8.4 GB
Too big Get file →
Q4_K_S7.1 GB 8.4 GB
Too big Get file →
Q4_K_M7.5 GB 8.8 GB
Too big Get file →
Q5_K_S8.5 GB 9.8 GB
Too big Get file →
Q5_K_M8.7 GB 10.0 GB
Too big Get file →
Q6_K10.1 GB 11.4 GB
Too big Get file →

What GPU do you need for Blue Rose Coder 12.3B Instruct 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 Q2_K (4.7 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_XS (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.4 GB in use).

Which Blue Rose Coder 12.3B Instruct i1 quant should you choose?

Q4_K_M is the usual starting point for Blue Rose Coder 12.3B Instruct i1: it balances file size and quality well. Here it is a 7.5 GB file.

If memory is tight, the smallest file is IQ1_S at 2.9 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

Architectureqwen2
Parameters12.3B
Layers48
Trained context32,768 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyBlue
Downloads (HF)489
Last updated2024-12-11

Frequently asked questions about Blue Rose Coder 12.3B Instruct i1

How much VRAM does Blue Rose Coder 12.3B Instruct i1 need?

About 8.8 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 Blue Rose Coder 12.3B Instruct i1 on an 8 GB GPU?

Yes, with IQ4_XS: the 6.7 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 Blue Rose Coder 12.3B Instruct i1 GGUF?

It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.8 GB, IQ2_S is 4.0 GB, IQ2_M is 4.3 GB and 19 more.

What context length does Blue Rose Coder 12.3B Instruct 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 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Blue Rose Coder 12.3B Instruct i1 GGUF?

The files are on Hugging Face in the mradermacher/Blue-Rose-Coder-12.3B-Instruct-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Blue-Rose-Coder-12.3B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Blue models

All Blue →

Other medium models

All medium models →