Minerva GGUF models

70 GGUF models in the Minerva family, quantized by 21 uploaders. Sizes run from 30M to 79.7B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MI
Minerva 3B base v1.0
Minerva · sapienzanlp
Params2.89B
Context—
Smallest11.6 GB
GGUF
MI
Minerva 3B base RAG
Minerva · QuantFactory
Params2.89B
Context16K
Q4_K_M1.8 GB
GGUF
MI
Minerva
Minerva · RichardErkhov
Params2.89B
Context16K
Q4_K_M1.8 GB
GGUF
MI
Minerva 1B Base v1.0
Minerva · mradermacher
Params1.01B
Context16K
Q4_K_M0.6 GB
GGUF
MI
Minerva 3B Base v1.0
Minerva · mradermacher
Params2.89B
Context16K
Q4_K_M1.8 GB
GGUF
MI
Minerva 350M Base v1.0
Minerva · mradermacher
Params352M
Context16K
Q4_K_M0.3 GB
GGUF
MI
Minerva 10b i1
Minerva · mradermacher
Params10.1B
Context1000K
Q4_K_M6.2 GB
GGUF
MI
Minerva 3B Base v1.0
Minerva · mradermacher
Params2.89B
Context16K
Q4_K_M1.8 GB
GGUF
MI
Minerva-MoE-2x3B
Minerva · mradermacher
Params5.1B
Context16K
Q4_K_M3.1 GB
GGUF
MI
Minerva 1B Base v1.0
Minerva · mradermacher
Params1.01B
Context16K
Q4_K_M0.6 GB
GGUF
MI
Minerva-MoE-3x3B
Minerva · mradermacher
Params7.3B
Context16K
Q4_K_M4.4 GB
GGUF
MI
Minerva 7b Inst
Minerva · sapienzanlp
Params7.4B
Context4K
Q4_K_M4.5 GB
GGUF
MI
Minerva 7b i1
Minerva · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
MI
Minerva 14b i1
Minerva · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
MI
Minerva DPO v0.1
Minerva · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
Tool use
MI
Minerva v0.1
Minerva · AxoneSystem
Params30M
Context512
Smallest0.1 GB
GGUF
MI
Minerva 350M Base v1.0
Minerva · mradermacher
Params352M
Context16K
Q4_K_M0.3 GB
GGUF
MI
Minerva 7b
Minerva · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
MI
Minerva 14b
Minerva · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
MI
Minerva 1.5b i1
Minerva · mradermacher
Params1.78B
Context32K
Q4_K_M1.1 GB
Tool use
MI
Minerva
Minerva · tensorblock
Params2.89B
Context16K
Smallest1.1 GB
GGUF
MI
sapienzanlp.Minerva 7B Instruct v1.0
Minerva · DevQuasar-5
Params7.4B
Context4K
Q4_K_M4.5 GB
GGUF
MI
Minerva 8b i1
Minerva · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
MI
Minerva 1.5b V0.2 i1
Minerva · mradermacher
Params1.78B
Context32K
Q4_K_M1.1 GB
Tool use
MI
Minerva 8b
Minerva · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
MI
Minerva 3B Instruct v1.0 Q4 K M
Minerva · mudler
Params2.89B
Context16K
Q4_K_M1.8 GB
GGUF
MI
Minerva 14b
Minerva · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
MI
sapienzanlp.Minerva 3B Base v1.0
Minerva · DevQuasar-6
Params2.89B
Context16K
Q4_K_M1.8 GB
GGUF
MI
Minerva 3B Instruct v1.0 Q5 K M
Minerva · NikolayKozloff
Params2.89B
Context16K
Smallest2.1 GB
GGUF
MI
Minerva 1.5b V0.2
Minerva · mradermacher
Params1.78B
Context32K
Q4_K_M1.1 GB
Tool use

About the Minerva GGUF models

Minerva is represented on ggufmodels.com by 70 GGUF models, quantized by 21 uploaders on Hugging Face. The most downloaded are Minerva 3B base v1.0, Minerva 3B base RAG and Minerva. Parameter counts run from 30M to 79.7B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Minerva model is between 0.3 to 48.5 GB, which is the quant most people start with. Most files come from mradermacher (23), roleplaiapp (12) and mudler (8). The quants you will meet most often are Q4_K_M (34), Q6_K (32), Q5_K_M (32) and Q3_K_M (29), where the number is how many models offer that quant.

Frequently asked questions

Which Minerva GGUF should I download?

The most downloaded Minerva GGUF here is Minerva 3B base v1.0. 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 Minerva model need?

Q4_K_M files of Minerva models on this site range from 0.3 to 48.5 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 Minerva GGUF files come from?

The most common quantizers here are mradermacher, roleplaiapp and mudler. 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