CO

CombinaTrix 7B

CombinatrixGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.9 GB
Quick answer

CombinaTrix 7B needs about 6.1 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 2.9 GB (Q2_K) to 7.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

CombinaTrix 7B – a 7.24B llama model in GGUF format

CombinaTrix 7B is a 7.24B parameter llama model. It was created by merging several 7B models using LazyMergekit. The model is released under the apache-2.0 license.

Good at

  • Large context handling
  • Efficient inference with low‑bit quants
  • Stable performance on standard workloads

Limits

  • No vision support
  • Requires 8k context for full performance
  • No mixture of experts

Best for

  • Chatbots needing 8k context
  • Local inference on mid‑range GPUs
  • Research prototyping with low‑bit quantization

Who it’s for. Developers and researchers who need a 7B llama model that can run locally with a variety of quantizations. The model is suitable for projects that require a moderate context window and can operate within the constraints of the apache-2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.9 GB 4.4 GB
Fits Get file →
IQ3_XS3.2 GB 4.7 GB
Fits Get file →
Q3_K_S3.3 GB 4.9 GB
Fits Get file →
IQ3_S3.3 GB 4.9 GB
Fits Get file →
IQ3_M3.4 GB 5.0 GB
Fits Get file →
Q3_K_M3.7 GB 5.2 GB
Fits Get file →
Q3_K_L4.0 GB 5.6 GB
Fits Get file →
IQ4_XS4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.3 GB 5.9 GB
Fits Get file →
Q4_K_M4.5 GB 6.1 GB
Fits Get file →
Q5_K_S5.2 GB 6.7 GB
Fits Get file →
Q5_K_M5.3 GB 6.9 GB
Fits Get file →
Q6_K6.1 GB 7.7 GB
Tight Get file →
Q8_07.8 GB 9.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.52 GB, estimated memory 6.1 GB) or Q5_K_S (5.15 GB, 6.7 GB). For 12 GB VRAM, Q5_K_M (5.29 GB, 6.9 GB) or Q6_K (6.1 GB, 7.7 GB) are suitable. Higher‑bit quants like Q8_0 require 9.4 GB memory and 7.82 GB file size.

What GPU do you need for CombinaTrix 7B?

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 Q4_K_S (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.8 GB file, about 9.4 GB in use).

Which CombinaTrix 7B quant should you choose?

Q4_K_M is the usual starting point for CombinaTrix 7B: it balances file size and quality well. Here it is a 4.5 GB file.

The Q8_0 file is 7.8 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 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

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,559
Last updated2024-05-06

Frequently asked questions about CombinaTrix 7B

How much VRAM does CombinaTrix 7B need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 4.5 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 CombinaTrix 7B on an 8 GB GPU?

Yes, with Q6_K: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of CombinaTrix 7B GGUF?

It depends on the quant: Q2_K is 2.9 GB, IQ3_XS is 3.2 GB, Q3_K_S is 3.3 GB, IQ3_S is 3.3 GB, IQ3_M is 3.4 GB, Q3_K_M is 3.7 GB and 8 more.

What context length does CombinaTrix 7B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download CombinaTrix 7B GGUF?

The files are on Hugging Face in the mradermacher/CombinaTrix-7B-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 CombinaTrix 7B 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 CombinaTrix 7B on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_S quants will fit within 8 GB VRAM with some headroom.

Does the model support vision tasks?

No, CombinaTrix 7B does not include vision capabilities.

What context length does the model support?

The model was trained with 32768 tokens and performs best with an 8k context window.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other small models

All small models →