Moe GGUF models

74 GGUF models in the Moe family, quantized by 15 uploaders. Sizes run from 2M to 60.8B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MO
L3 4X8B MOE Dark Planet Infinite 25B
Moe · DavidAU
Params24.9B
Context8K
Q4_K_M15.2 GB
Roleplay
MO
Dark Planet 8D Mirrored Chaos
Moe · DavidAU
Params47.5B
Context8K
Q4_K_M29.0 GB
Roleplay
MO
L3.1 MOE 6X8B Dark Reasoning Dantes Peak HORROR R1 Uncensored 36B
Moe · DavidAU
Params36.2B
Context128K
Q4_K_M22.0 GB
ReasoningRoleplay
MO
L3.1 MOE 8X8B Dark Planet 8D Mirrored Chaos Uncensored 47B
Moe · DavidAU
Params47.5B
Context128K
Q4_K_M29.0 GB
Roleplay
MO
Moe 4x7b reason code qa i1
Moe · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
CodingReasoning
MO
L3 MOE 4x8B Dark Planet Rising 25B i1
Moe · mradermacher
Params25B
Context8K
Q4_K_M15.2 GB
GGUF
MO
L3.2 8X4B MOE V2 Dark Champion Inst 21B Uncen Ablit
Moe · mradermacher
Params21B
Context128K
Q4_K_M12.9 GB
GGUF
MO
GK-MoE-0.1
Moe · mradermacher
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
MO
L3 MOE 4x8B Dark Planet Rebel FURY 25B
Moe · DavidAU
Params25B
Context8K
Q4_K_M15.2 GB
Roleplay
MO
L3.1 MOE 6X8B Dark Reasoning Dantes Peak HORROR R1 Uncensored 36B
Moe · Jaedwards1986
Params36.2B
Context128K
Q4_K_M22.0 GB
ReasoningRoleplay
MO
Moe 4x7b reason code qa
Moe · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
CodingReasoning
MO
L3.2 8X4B MOE V2 Dark Champion Inst 21B Uncen Ablit
Moe · mradermacher
Params21B
Context128K
Q4_K_M12.9 GB
GGUF
MO
MoE Girl 1BA 7BT i1
Moe · mradermacher
Params6.92B
Context8K
Q4_K_M4.2 GB
Roleplay
MO
L3 MOE 4x8B Dark Planet Rebel FURY 25B
Moe · mradermacher
Params24.9B
Context8K
Q4_K_M15.2 GB
GGUF
MO
L3.1 MOE 8X8B Dark Planet 8D Mirrored Chaos Uncensored 47B i1
Moe · mradermacher
Params47.5B
Context128K
Q4_K_M29.0 GB
GGUF
MO
L3.1 MOE 6X8B Dark Reasoning Dantes Peak Hermes R1 Uncensored 36B
Moe · mradermacher
Params36.2B
Context128K
Q4_K_M22.0 GB
ReasoningRoleplayTool use
MO
L3.1 MOE 4X8B Dark Reasoning Super Nova RP Hermes R1 Uncensored 25B
Moe · mradermacher
Params24.9B
Context128K
Q4_K_M15.2 GB
ReasoningRoleplayTool use
MO
L3.1 Moe 2x8B v0.2
Moe · mradermacher
Params13.7B
Context128K
Q4_K_M8.3 GB
GGUF
MO
Dark Planet 8D Mirrored Chaos
Moe · mradermacher
Params47.5B
Context8K
Q4_K_M29.0 GB
Roleplay
MO
Moe 10b A1B 8k Wsd Lr3E4 1t
Moe · mradermacher
Params10.5B
Context8K
Q4_K_M6.4 GB
GGUF
MO
MoE Girl 1BA 7BT
Moe · mradermacher
Params6.92B
Context8K
Q4_K_M4.2 GB
Roleplay
MO
MoE Girl 800MA 3BT
Moe · mradermacher
Params3.37B
Context8K
Q4_K_M2.1 GB
Roleplay
MO
L3.1 Moe 2x8B v0.2 i1
Moe · mradermacher
Params13.7B
Context128K
Q4_K_M8.3 GB
GGUF
MO
Dark Planet 8D Mirrored Chaos
Moe · mradermacher
Params47.5B
Context8K
Q4_K_M29.0 GB
Roleplay
MO
Moe 3x7b QA Code Inst
Moe · mradermacher
Params18.5B
Context32K
Q4_K_M11.2 GB
CodingReasoning
MO
L3.1 MOE 4X8B Dark Reasoning Dark Planet Hermes R1 Uncensored E32 25B
Moe · mradermacher
Params24.9B
Context128K
Q4_K_M15.2 GB
ReasoningRoleplayTool use
MO
FL 12B MoE 2 Safetensors
Moe · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
MO
MoE-Girl-1BA-7BT
Moe · allura-org
Params6.92B
Context8K
Q4_K_M4.2 GB
GGUF
MO
L3 MOE 4X8B Grand Horror 25B
Moe · mradermacher
Params24.9B
Context8K
Q4_K_M15.2 GB
GGUF
MO
L3 MOE 4x8B Dark Planet Rising 25B
Moe · mradermacher
Params24.9B
Context8K
Q4_K_M15.2 GB
GGUF

About the Moe GGUF models

Moe is represented on ggufmodels.com by 74 GGUF models, quantized by 15 uploaders on Hugging Face. The most downloaded are L3 4X8B MOE Dark Planet Infinite 25B, Dark Planet 8D Mirrored Chaos and L3.1 MOE 6X8B Dark Reasoning Dantes Peak HORROR R1 Uncensored 36B. Parameter counts run from 2M to 60.8B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Moe model is between 0.8 to 35.4 GB, which is the quant most people start with. Most files come from mradermacher (49), DavidAU (5) and tensorblock (4). The quants you will meet most often are Q2_K (63), Q6_K (62), Q4_K_M (62) and Q5_K_M (61), where the number is how many models offer that quant.

Frequently asked questions

Which Moe GGUF should I download?

The most downloaded Moe GGUF here is L3 4X8B MOE Dark Planet Infinite 25B. 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 Moe model need?

Q4_K_M files of Moe models on this site range from 0.8 to 35.4 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 Moe GGUF files come from?

The most common quantizers here are mradermacher, DavidAU 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