Mamba GGUF models

90 GGUF models in the Mamba family, quantized by 25 uploaders. Sizes run from 129M to 7.27B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MA
mamba 130m hf
Mamba · QuantFactory
Params129M
Context1024K
Q4_K_M0.1 GB
GGUF
MA
Mamba2 130m Hf
Mamba · rpatel622
Params168M
Context1024K
Smallest0.2 GB
GGUF
MA
Mamba 370m Hf
Mamba · mradermacher
Params372M
Context1024K
Q4_K_M0.2 GB
GGUF
MA
Mamba 790m Hf
Mamba · mradermacher
Params790M
Context1024K
Q4_K_M0.5 GB
GGUF
MA
Mamba 130m Hf
Mamba · mradermacher
Params129M
Context1024K
Q4_K_M0.1 GB
GGUF
MA
Mamba 2.8b Hf
Mamba · mradermacher
Params2.77B
Context1024K
Q4_K_M1.6 GB
GGUF
MA
Mamba 1.4b Hf
Mamba · mradermacher
Params1.37B
Context1024K
Q4_K_M0.8 GB
GGUF
MA
Mamba gpt 3B v4 ggml and
Mamba · Aryanne
Params3.43B
Context2K
Smallest2.0 GB
GGUF
MA
Mamba Gpt 7b v1
Mamba · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MA
Mamba Gpt 7b v2
Mamba · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MA
mamba gpt 7b i1
Mamba · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MA
mamba-distill-7b
Mamba · mradermacher
Params7.27B
Context1024K
Q4_K_M4.2 GB
Reasoning
MA
mamba-2.8b-hf
Mamba · bartowski
Params2.77B
Context1024K
Q4_K_M2.0 GB
GGUF
MA
gguf mamba 130m hf
Mamba · Felladrin
Params129M
Context1024K
Q4_K_M0.1 GB
GGUF
MA
mamba-2.8b-hf
Mamba · leliuga
Params2.77B
Context1024K
Q4_K_M2.0 GB
GGUF
MA
Mamba 3B
Mamba · mradermacher
Params2.77B
Context1024K
Q4_K_M1.6 GB
GGUF
MA
mamba 2.8b hf
Mamba · QuantFactory
Params2.77B
Context1024K
Q4_K_M1.6 GB
GGUF
MA
Mamba 3B
Mamba · mradermacher
Params2.77B
Context1024K
Q4_K_M1.6 GB
GGUF
MA
mamba-2.8b-hf
Mamba · jpodivin
Params2.77B
Context1024K
Smallest1.4 GB
GGUF
MA
Mamba 1.4b Instruct Hf
Mamba · RichardErkhov
Params1.37B
Context1024K
Q4_K_M0.8 GB
GGUF
MA
Mamba 3B Slimpj
Mamba · mradermacher
Params2.77B
Context1024K
Q4_K_M1.6 GB
GGUF
MA
mamba-130m-hf
Mamba · RichardErkhov
Params129M
Context1024K
Q4_K_M0.1 GB
GGUF
MA
Mamba 790M
Mamba · mradermacher
Params793M
Context1024K
Q4_K_M0.5 GB
GGUF
MA
Mamba 790M
Mamba · mradermacher
Params793M
Context1024K
Q4_K_M0.5 GB
GGUF
MA
Mamba 2.8b Ultrachat Hf
Mamba · RichardErkhov
Params2.77B
Context1024K
Q4_K_M1.6 GB
GGUF
MA
Mamba Gpt 7b v1
Mamba · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MA
Mamba 370M
Mamba · mradermacher
Params372M
Context1024K
Q4_K_M0.2 GB
GGUF
MA
State Spaces Mamba 370m Hf
Mamba · tensorblock
Params372M
Context1024K
Smallest0.2 GB
GGUF
MA
Mamba 2.8b Hf
Mamba · mradermacher
Params2.77B
Context1024K
Q4_K_M1.6 GB
GGUF
MA
mamba-2.8b
Mamba · RichardErkhov
Params2.77B
Context1024K
Q4_K_M2.0 GB
GGUF

About the Mamba GGUF models

Mamba is represented on ggufmodels.com by 90 GGUF models, quantized by 25 uploaders on Hugging Face. The most downloaded are mamba 130m hf, Mamba2 130m Hf and Mamba 370m Hf. Parameter counts run from 129M to 7.27B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Mamba model is between 0.1 to 4.4 GB, which is the quant most people start with. Most files come from mradermacher (40), RichardErkhov (12) and tensorblock (8). The quants you will meet most often are Q2_K (71), Q3_K_M (66), Q4_K_M (65) and Q6_K (64), where the number is how many models offer that quant.

Frequently asked questions

Which Mamba GGUF should I download?

The most downloaded Mamba GGUF here is mamba 130m hf. 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 Mamba model need?

Q4_K_M files of Mamba models on this site range from 0.1 to 4.4 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 Mamba GGUF files come from?

The most common quantizers here are mradermacher, RichardErkhov and tensorblock. 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