CH

Chunky Merge 22B i1

ChunkyGGUF by mradermacherUpdated 2024-11-13
Download on Hugging Face
Parameters12.9B
Context128K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

Chunky Merge 22B i1 needs about 9.3 GB of memory at Q4_K_M (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.8 GB (IQ1_S) to 10.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Chunky Merge 22B i1 – 12.9B llama model with tool support

Chunky Merge 22B i1 is a 12.9B parameter llama model merged from multiple 22B models. It supports tool usage and has a trained context of 131072 tokens. The model is available in many GGUF quantizations.

Good at

  • Tool integration
  • Large context handling
  • High parameter count

Limits

  • No vision support
  • License not specified
  • Large VRAM needed for higher quants

Best for

  • Tool‑driven applications
  • Long‑form text generation
  • Complex reasoning tasks

Who it’s for. Developers and researchers needing a large llama model with tool support. The model is suitable for local inference using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.8 GB 4.4 GB
Fits Get file →
IQ1_M3.1 GB 4.7 GB
Fits Get file →
IQ2_XXS3.5 GB 5.1 GB
Fits Get file →
IQ2_XS3.9 GB 5.5 GB
Fits Get file →
IQ2_S4.1 GB 5.7 GB
Fits Get file →
IQ2_M4.5 GB 6.0 GB
Fits Get file →
Q2_K4.8 GB 6.4 GB
Fits Get file →
IQ3_XXS5.0 GB 6.6 GB
Fits Get file →
IQ3_XS5.4 GB 6.9 GB
Fits Get file →
Q3_K_S5.6 GB 7.2 GB
Fits Get file →
IQ3_S5.6 GB 7.2 GB
Tight Get file →
IQ3_M5.9 GB 7.4 GB
Tight Get file →
Q3_K_M6.3 GB 7.8 GB
Tight Get file →
Q3_K_L6.8 GB 8.4 GB
Too big Get file →
IQ4_XS6.9 GB 8.5 GB
Too big Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_K_S7.4 GB 8.9 GB
Too big Get file →
Q4_K_M7.7 GB 9.3 GB
Too big Get file →
Q5_K_S8.9 GB 10.5 GB
Too big Get file →
Q5_K_M9.1 GB 10.7 GB
Too big Get file →
Q6_K10.6 GB 12.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.85 GB, memory 4.4 GB at 8k context) or IQ1_M (3.1 GB, 4.7 GB). If you have 12 GB VRAM, Q4_K_M (7.74 GB, 9.3 GB) or Q5_K_S (8.89 GB, 10.5 GB) are viable. Higher quants like Q6_K require more than 12 GB VRAM.

What GPU do you need for Chunky Merge 22B 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 (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.3 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.1 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.6 GB file, about 12.1 GB in use).

Which Chunky Merge 22B i1 quant should you choose?

Q4_K_M is the usual starting point for Chunky Merge 22B i1: it balances file size and quality well. Here it is a 7.7 GB file.

If memory is tight, the smallest file is IQ1_S at 2.8 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
Parameters12.9B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyChunky
Downloads (HF)1,053
Last updated2024-11-13

Frequently asked questions about Chunky Merge 22B i1

How much VRAM does Chunky Merge 22B i1 need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.7 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 Chunky Merge 22B i1 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.3 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Chunky Merge 22B i1 GGUF?

It depends on the quant: IQ1_S is 2.8 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.1 GB, IQ2_M is 4.5 GB and 18 more.

What context length does Chunky Merge 22B i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Chunky Merge 22B i1 GGUF?

The files are on Hugging Face in the mradermacher/Chunky-Merge-22B-i1-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 Chunky Merge 22B i1 on 8 GB VRAM?

Yes, with the IQ1_S or IQ1_M quant, which use about 4.4–4.7 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the trained context length?

The model was trained with a context of 131072 tokens.

Other GGUFs of Chunky-Merge-22B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Chunky models

All Chunky →

Other medium models

All medium models →