MA

magnum v4 27b

MagnumGGUF by mradermacherUpdated 2024-11-26
Download on Hugging Face
Parameters27.2B
Context8K
Layers46
Architecturegemma2
Smallest quant10.4 GB
Quick answer

magnum v4 27b needs about 20.2 GB of memory at Q4_K_M (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.4 GB (Q2_K) to 28.9 GB (Q8_0).

Magnum v4 27b – a Gemma2‑based model fine‑tuned to emulate Claude 3 prose

Magnum v4 27b is a 27.2B‑parameter Gemma2 model fine‑tuned on chatML. It was trained for 2 epochs on 8xH100 GPUs. The model supports 8192‑token context and is released under the gemma license.

Good at

  • High‑quality conversational text
  • Claude‑style prose emulation
  • Large context handling

Limits

  • No vision support
  • License is gemma
  • Requires 8k context for full capability

Best for

  • Chatbots needing Claude‑style responses
  • Content generation with long context
  • Fine‑tuning on custom datasets

Who it’s for. Developers building chat applications that require high‑quality, long‑context responses. Researchers needing a large Gemma2 model for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.4 GB 14.0 GB
Too big Get file →
Q3_K_S12.2 GB 15.8 GB
Too big Get file →
Q3_K_M13.4 GB 17.0 GB
Too big Get file →
Q3_K_L14.5 GB 18.1 GB
Too big Get file →
IQ4_XS14.9 GB 18.5 GB
Too big Get file →
Q4_K_S15.7 GB 19.3 GB
Too big Get file →
Q4_K_M16.6 GB 20.2 GB
Too big Get file →
Q5_K_S18.9 GB 22.5 GB
Too big Get file →
Q5_K_M19.4 GB 23.0 GB
Too big Get file →
Q6_K22.3 GB 25.9 GB
Too big Get file →
Q8_028.9 GB 32.5 GB
Too big Get file →

For 8 GB VRAM use Q2_K (10.45 GB file, 14 GB memory). For 12 GB VRAM use Q3_K_S (12.17 GB file, 15.8 GB memory). For 16 GB VRAM use Q4_K_M (16.65 GB file, 20.2 GB memory).

What GPU do you need for magnum v4 27b?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_S (12.2 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.3 GB file, about 25.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.9 GB file, about 32.5 GB in use).

Which magnum v4 27b quant should you choose?

Q4_K_M is the usual starting point for magnum v4 27b: it balances file size and quality well. Here it is a 16.6 GB file.

The Q8_0 file is 28.9 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 10.4 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

Architecturegemma2
Parameters27.2B
Layers46
Trained context8,192 tokens
KV cache (fp16)368 KB per token

Source

Quantized bymradermacher
FamilyMagnum
Licensegemma
Downloads (HF)3,117
Last updated2024-11-26

Frequently asked questions about magnum v4 27b

How much VRAM does magnum v4 27b need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 16.6 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 magnum v4 27b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of magnum v4 27b GGUF?

It depends on the quant: Q2_K is 10.4 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.4 GB, Q3_K_L is 14.5 GB, IQ4_XS is 14.9 GB, Q4_K_S is 15.7 GB and 5 more.

What context length does magnum v4 27b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.

Where can I download magnum v4 27b GGUF?

The files are on Hugging Face in the mradermacher/magnum-v4-27b-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 magnum v4 27b use?

Hugging Face lists the license as gemma. 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 Magnum v4 27b on 8 GB VRAM?

Yes, using the Q2_K quant which requires 14 GB memory at 8k context, which is within 8 GB VRAM with efficient batching.

Does this model support image input?

No, Magnum v4 27b does not have vision capabilities.

Where can I download the GGUF files?

GGUF files are available from the Hugging Face repo mradermacher/magnum-v4-27b-GGUF.

Other GGUFs of magnum-v4-27b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Magnum models

All Magnum →

Other medium models

All medium models →