MU

MuMath-Code-CL-13B

MumathGGUF by mradermacherUpdated 2024-05-24
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

MuMath-Code-CL-13B needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 2.5 GB (Q2_K) to 13.5 GB (F16).

MuMath-Code-CL-13B – 6.74B llama model focused on coding

MuMath-Code-CL-13B is a 6.74B parameter llama model optimized for coding tasks. It supports a 16384 token context window and is available in multiple GGUF quantizations. The model is provided by mradermacher and is a direct quantization of weihao1/MuMath-Code-CL-13B.

Good at

  • Coding assistance
  • Code generation
  • Programming logic

Limits

  • No vision support
  • License not specified
  • Large context requires significant VRAM

Best for

  • Writing scripts
  • Debugging code
  • Explaining programming concepts

Who it’s for. Developers and researchers who need a lightweight coding assistant. The model is suitable for local deployment on machines with sufficient VRAM to handle the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 7.3 GB
Tight Get file →
IQ3_XS2.8 GB 7.6 GB
Tight Get file →
IQ3_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
IQ3_M3.1 GB 7.9 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
IQ4_XS3.6 GB 8.4 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
F1613.5 GB 18.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (4.08 GB file, ~8.9 GB memory). For 12 GB VRAM use Q6_K (5.53 GB file, ~10.3 GB memory). For higher fidelity with 18 GB VRAM use F16 (13.48 GB file, ~18.3 GB memory).

What GPU do you need for MuMath-Code-CL-13B?

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 (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which MuMath-Code-CL-13B quant should you choose?

Q4_K_M is the usual starting point for MuMath-Code-CL-13B: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.5 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
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyMumath
Downloads (HF)1,204
Last updated2024-05-24

Frequently asked questions about MuMath-Code-CL-13B

How much VRAM does MuMath-Code-CL-13B need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 MuMath-Code-CL-13B on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MuMath-Code-CL-13B GGUF?

It depends on the quant: Q2_K is 2.5 GB, IQ3_XS is 2.8 GB, IQ3_S is 2.9 GB, Q3_K_S is 2.9 GB, IQ3_M is 3.1 GB, Q3_K_M is 3.3 GB and 9 more.

What context length does MuMath-Code-CL-13B support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download MuMath-Code-CL-13B GGUF?

The files are on Hugging Face in the mradermacher/MuMath-Code-CL-13B-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 MuMath-Code-CL-13B on 8 GB VRAM?

Yes, use the Q4_K_M quantization which requires approximately 8.9 GB VRAM at 8k context.

Does this model support image inputs?

No, MuMath-Code-CL-13B does not have vision capabilities.

What is the context length of this model?

The model supports a context length of 16384 tokens.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mumath models

All Mumath →

Other small models

All small models →