DE

DeepCode 7B Aurora v3

DeepcodeGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters6.91B
Context4K
Layers30
Architecturellama
Smallest quant2.7 GB
Quick answer

DeepCode 7B Aurora v3 needs about 8.8 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 2.7 GB (Q2_K) to 7.3 GB (Q8_0).

DeepCode 7B Aurora v3 – a 6.91B llama model in GGUF format

DeepCode 7B Aurora v3 is a 6.91B llama model merged from multiple DeepSeek math variants. It is available in a range of static quantizations for llama.cpp. The model is licensed under apache-2.0 and supports a 4096 token context.

Good at

  • Math reasoning
  • Instruction following
  • Code generation

Limits

  • No vision support
  • Requires 8k context for estimates
  • License is apache-2.0

Best for

  • Math problem solving
  • Writing code snippets
  • Educational tutoring

Who it’s for. Developers and researchers who need a compact, math‑focused LLM for local inference. The model is suitable for use cases that fit within a 4096 token context window and can run on systems with sufficient VRAM for the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 5.2 GB
Fits Get file →
IQ3_XS3.0 GB 5.5 GB
Fits Get file →
IQ3_S3.1 GB 5.7 GB
Fits Get file →
Q3_K_S3.1 GB 5.7 GB
Fits Get file →
IQ3_M3.3 GB 5.8 GB
Fits Get file →
Q3_K_M3.5 GB 6.0 GB
Fits Get file →
Q3_K_L3.7 GB 6.3 GB
Fits Get file →
IQ4_XS3.8 GB 6.3 GB
Fits Get file →
Q4_K_S4.0 GB 6.5 GB
Fits Get file →
Q4_K_M4.2 GB 6.7 GB
Fits Get file →
Q5_K_S4.8 GB 7.3 GB
Tight Get file →
Q5_K_M4.9 GB 7.4 GB
Tight Get file →
Q6_K5.7 GB 8.2 GB
Too big Get file →
Q8_07.3 GB 9.9 GB
Too big Get file →

For 8 GB VRAM, Q4_K_M (4.22 GB file, 8.8 GB memory at 8k context) is a good balance. If memory is tighter, Q3_K_M (3.46 GB file, 8 GB memory) or Q3_K_S (3.14 GB file, 7.7 GB memory) are viable. For maximum quality, Q5_K_M (4.93 GB file, 9.5 GB memory) can be used on systems with >10 GB VRAM.

What GPU do you need for DeepCode 7B Aurora v3?

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 (3.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 11.9 GB in use).

Which DeepCode 7B Aurora v3 quant should you choose?

Q4_K_M is the usual starting point for DeepCode 7B Aurora v3: it balances file size and quality well. Here it is a 4.2 GB file.

The Q8_0 file is 7.3 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 2.7 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
Parameters6.91B
Layers30
Trained context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized bymradermacher
FamilyDeepcode
Licenseapache-2.0
Downloads (HF)552
Last updated2024-05-06

Frequently asked questions about DeepCode 7B Aurora v3

How much VRAM does DeepCode 7B Aurora v3 need?

About 8.8 GB at Q4_K_M with an 8K context window. That is the 4.2 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 DeepCode 7B Aurora v3 on an 8 GB GPU?

Yes, with Q3_K_M: the 3.5 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 DeepCode 7B Aurora v3 GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, IQ3_S is 3.1 GB, Q3_K_S is 3.1 GB, IQ3_M is 3.3 GB, Q3_K_M is 3.5 GB and 8 more.

What context length does DeepCode 7B Aurora v3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.

Where can I download DeepCode 7B Aurora v3 GGUF?

The files are on Hugging Face in the mradermacher/DeepCode-7B-Aurora-v3-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 DeepCode 7B Aurora v3 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 DeepCode 7B Aurora v3 on 8 GB VRAM?

Yes, the Q4_K_M quant uses 8.8 GB memory at 8k context, which fits within 8 GB VRAM with some overhead. Use a smaller quant if needed.

Does the model support vision tasks?

No, the model has no vision capabilities and is designed for text and code tasks only.

What context length does the model support?

The model was trained with 4096 tokens and performs best within that context length.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Deepcode models

All Deepcode →

Other small models

All small models →