Magnum GGUF models

271 GGUF models in the Magnum family, quantized by 49 uploaders. Sizes run from 1.5B to 123B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MA
magnum v4 12b
Magnum · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MA
MS3.2 24B Magnum Diamond
Magnum · Doctor-Shotgun
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
MA
Magnum v4 72b
Magnum · bartowski
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
MA
magnum v4 12b
Magnum · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MA
magnum v4 12b
Magnum · anthracite-org
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MA
L3.3 70B Magnum v4 SE
Magnum · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
MA
Magnum 12b v2
Magnum · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MA
magnum v3 9b chatml
Magnum · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MA
Magnum 12b v2.5 Kto
Magnum · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MA
Magnum v4 22b
Magnum · mradermacher
Params22.2B
Context32K
Q4_K_M13.3 GB
GGUF
MA
magnum v4 27b
Magnum · mradermacher
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
MA
magnum v4 27b
Magnum · bartowski
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
MA
Magnum v4 9b
Magnum · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MA
magnum v4 12b
Magnum · tensorblock
Params12.2B
Context1000K
Smallest4.8 GB
GGUF
MA
magnum v2 4b
Magnum · bartowski
Params4.51B
Context128K
Q4_K_M2.8 GB
GGUF
MA
Magnum Blackout Ataraxy 2 9b i1
Magnum · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MA
Magnum v4 22b
Magnum · bartowski
Params22.2B
Context32K
Q4_K_M13.3 GB
GGUF
MA
Magnum Picaro 0.7 v2 12b i1
Magnum · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MA
magnum v3 9b customgemma2
Magnum · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MA
Magnum v4 9b
Magnum · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MA
Magnum v4 9b Abliterated
Magnum · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MA
magnum 32b v2
Magnum · bartowski
Params32.5B
Context32K
Q4_K_M19.7 GB
GGUF
MA
Magnum Holland Sus Merge i1
Magnum · mradermacher
Params4.51B
Context128K
Q4_K_M2.8 GB
GGUF
MA
magnum v3 34b
Magnum · bartowski
Params34.4B
Context32K
Q4_K_M20.7 GB
GGUF
MA
magnum v2.5 12b kto
Magnum · anthracite-org
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MA
magnum-72b-v1
Magnum · Quant-Cartel
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
MA
magnum v4 27b
Magnum · anthracite-org
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
MA
magnum v4 72b
Magnum · anthracite-org
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
MA
Magnum v3 27b Kto
Magnum · mradermacher
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
MA
magnum 32b v1 i1
Magnum · mradermacher
Params32.5B
Context32K
Q4_K_M19.7 GB
GGUF

About the Magnum GGUF models

Magnum is represented on ggufmodels.com by 271 GGUF models, quantized by 49 uploaders on Hugging Face. The most downloaded are magnum v4 12b, MS3.2 24B Magnum Diamond and Magnum v4 72b. Parameter counts run from 1.5B to 123B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Magnum model is between 1.0 to 73.2 GB, which is the quant most people start with. Most files come from mradermacher (138), bartowski (20) and anthracite-org (13). The quants you will meet most often are Q4_K_M (220), Q5_K_M (209), Q2_K (208) and Q6_K (201), where the number is how many models offer that quant.

Frequently asked questions

Which Magnum GGUF should I download?

The most downloaded Magnum GGUF here is magnum v4 12b. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Magnum model need?

Q4_K_M files of Magnum models on this site range from 1.0 to 73.2 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Magnum GGUF files come from?

The most common quantizers here are mradermacher, bartowski and anthracite-org. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing