CA

Calme 12B Instruct v0.1

CalmeGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters12.5B
Context32K
Layers56
Architecturellama
Smallest quant4.6 GB
Quick answer

Calme 12B Instruct v0.1 needs about 9.9 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 14 quants, from 4.6 GB (Q2_K) to 13.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Calme 12B Instruct v0.1 – 12.5B parameter Llama model

Calme 12B Instruct v0.1 is a 12.5 billion parameter Llama architecture model fine‑tuned for instruction following. It supports a 32,768 token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Long‑form text generation
  • Multilingual support

Limits

  • No vision capabilities
  • Requires 32,768 token context
  • No mixture of experts

Best for

  • Chatbots needing long context
  • Content drafting with extended prompts
  • Research prototyping on commodity hardware

Who it’s for. Developers and researchers who need a large instruction‑tuned Llama model that can run on consumer GPUs. The model is suitable for applications that require extended context and can tolerate the memory demands of higher‑bit quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.6 GB 7.0 GB
Fits Get file →
IQ3_XS5.2 GB 7.5 GB
Tight Get file →
Q3_K_S5.4 GB 7.8 GB
Tight Get file →
IQ3_S5.4 GB 7.8 GB
Tight Get file →
IQ3_M5.6 GB 8.0 GB
Too big Get file →
Q3_K_M6.0 GB 8.4 GB
Too big Get file →
Q3_K_L6.6 GB 8.9 GB
Too big Get file →
IQ4_XS6.8 GB 9.1 GB
Too big Get file →
Q4_K_S7.1 GB 9.5 GB
Too big Get file →
Q4_K_M7.5 GB 9.9 GB
Too big Get file →
Q5_K_S8.6 GB 11.0 GB
Too big Get file →
Q5_K_M8.8 GB 11.2 GB
Too big Get file →
Q6_K10.2 GB 12.6 GB
Too big Get file →
Q8_013.3 GB 15.6 GB
Too big Get file →

For 8 GB VRAM, the Q3_K_S quant (file size 5.41 GB, estimated memory 7.8 GB at 8 k context) is a good choice. If more VRAM is available, Q4_K_M (file size 7.51 GB, estimated memory 9.9 GB) offers better quality. Higher‑bit quants such as Q5_K_M or Q6_K provide improved fidelity but need 11.2 GB or 12.6 GB of VRAM respectively.

What GPU do you need for Calme 12B Instruct v0.1?

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 IQ3_M (5.6 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (8.8 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.3 GB file, about 15.6 GB in use).

Which Calme 12B Instruct v0.1 quant should you choose?

Q4_K_M is the usual starting point for Calme 12B Instruct v0.1: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.3 GB, about 1.8 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 4.6 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
Parameters12.5B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymradermacher
FamilyCalme
Licenseapache-2.0
Downloads (HF)1,168
Last updated2024-05-06

Frequently asked questions about Calme 12B Instruct v0.1

How much VRAM does Calme 12B Instruct v0.1 need?

About 9.9 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 Calme 12B Instruct v0.1 on an 8 GB GPU?

Yes, with IQ3_M: the 5.6 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 Calme 12B Instruct v0.1 GGUF?

It depends on the quant: Q2_K is 4.6 GB, IQ3_XS is 5.2 GB, Q3_K_S is 5.4 GB, IQ3_S is 5.4 GB, IQ3_M is 5.6 GB, Q3_K_M is 6.0 GB and 8 more.

What context length does Calme 12B Instruct v0.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Calme 12B Instruct v0.1 GGUF?

The files are on Hugging Face in the mradermacher/Calme-12B-Instruct-v0.1-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 Calme 12B Instruct v0.1 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.

Can I run Calme 12B Instruct v0.1 on 8 GB VRAM?

Yes, using the Q3_K_S quant will fit within 8 GB VRAM, with an estimated memory usage of 7.8 GB at 8 k context.

Does this model support vision tasks?

No, Calme 12B Instruct v0.1 is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of Calme-12B-Instruct-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Calme models

All Calme →

Other medium models

All medium models →