MO

MonarchCoder MoE 2x7B

MonarchcoderGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

MonarchCoder MoE 2x7B needs about 9.5 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 16 quants, from 4.9 GB (Q2_K) to 13.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MonarchCoder MoE 2x7B – a 12.9B parameter mixture of experts for coding

MonarchCoder MoE 2x7B is a 12.9B parameter model built as a mixture of experts. It merges AlphaMonarch-7B and Tess-Coder-7B-Mistral-v1.0 to enhance reasoning, conversation, and coding performance. The model is released under the apache-2.0 license.

Good at

  • Advanced coding tasks
  • Reasoning and problem solving
  • Conversational interactions

Limits

  • No vision support
  • Requires 8k context for full performance
  • Large VRAM needed for higher quants

Best for

  • Code generation and debugging
  • Technical Q&A sessions
  • Educational coding tutorials

Who it’s for. Developers and researchers needing a large, expert‑augmented model for coding and reasoning. The model is suitable for those who can allocate sufficient GPU memory and are comfortable with GGUF formats.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.9 GB 6.5 GB
Fits Get file →
IQ3_XS5.5 GB 7.0 GB
Fits Get file →
Q3_K_S5.7 GB 7.3 GB
Tight Get file →
IQ3_S5.8 GB 7.3 GB
Tight Get file →
IQ3_M5.9 GB 7.5 GB
Tight Get file →
Q3_K_M6.4 GB 7.9 GB
Tight Get file →
Q3_K_L6.9 GB 8.5 GB
Too big Get file →
IQ4_XS7.1 GB 8.7 GB
Too big Get file →
Q4_07.4 GB 9.0 GB
Too big Get file →
Q4_K_S7.5 GB 9.1 GB
Too big Get file →
IQ4_NL7.5 GB 9.1 GB
Too big Get file →
Q4_K_M7.9 GB 9.5 GB
Too big Get file →
Q5_K_S9.0 GB 10.6 GB
Too big Get file →
Q5_K_M9.3 GB 10.9 GB
Too big Get file →
Q6_K10.7 GB 12.3 GB
Too big Get file →
Q8_013.8 GB 15.4 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (4.91 GB, 6.5 GB memory) or IQ3_XS (5.45 GB, 7 GB memory). If 12 GB VRAM is available, Q4_K_M (7.94 GB, 9.5 GB memory) offers a good balance of size and quality. For the best performance with 15 GB VRAM, Q8_0 (13.81 GB, 15.4 GB memory) is recommended.

What GPU do you need for MonarchCoder MoE 2x7B?

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 (6.4 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.3 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 15.4 GB in use).

Which MonarchCoder MoE 2x7B quant should you choose?

Q4_K_M is the usual starting point for MonarchCoder MoE 2x7B: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 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 4.9 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
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,097
Last updated2024-05-06

Frequently asked questions about MonarchCoder MoE 2x7B

How much VRAM does MonarchCoder MoE 2x7B need?

About 9.5 GB at Q4_K_M with an 8K context window. That is the 7.9 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 MonarchCoder MoE 2x7B on an 8 GB GPU?

Yes, with Q3_K_M: the 6.4 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 MonarchCoder MoE 2x7B GGUF?

It depends on the quant: Q2_K is 4.9 GB, IQ3_XS is 5.5 GB, Q3_K_S is 5.7 GB, IQ3_S is 5.8 GB, IQ3_M is 5.9 GB, Q3_K_M is 6.4 GB and 10 more.

What context length does MonarchCoder MoE 2x7B 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 MonarchCoder MoE 2x7B GGUF?

The files are on Hugging Face in the mradermacher/MonarchCoder-MoE-2x7B-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 MonarchCoder MoE 2x7B 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 MonarchCoder MoE 2x7B on 8 GB VRAM?

Yes, the Q2_K quant requires 6.5 GB memory at 8k context, which fits within 8 GB VRAM.

Does the model support vision tasks?

No, MonarchCoder MoE 2x7B does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Monarchcoder models

All Monarchcoder →

Other medium models

All medium models →