now with high IQ
Gheorghe Chesler PRO
nightmedia
AI & ML interests
Nightmedia: human-Like AI and the MLX Deckard(qx) Formula
Donations are appreciated:
BTC:36d7U1n3MFaXgnNRAaEL3Pa3Hy6oFhM7XY
Recent Activity
updated a model about 7 hours ago
nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Qwythos-qx86-hi-mlx published a model about 8 hours ago
nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Qwythos-qx86-hi-mlx updated a model about 15 hours ago
nightmedia/SuperGemma-4-12b-abliterated-TNG-mxfp8-mlxOrganizations
in mxfp4, mxfp8, and Deckard(qx)
-
nightmedia/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx
Image-Text-to-Text • 8B • Updated • 570 • 2 -
nightmedia/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx
Image-Text-to-Text • 8B • Updated • 131 -
nightmedia/gemma-4-E4B-it-mxfp8-mlx
Any-to-Any • 3B • Updated • 35 • 2 -
nightmedia/gemma-4-E4B-it-mxfp4-mlx
Any-to-Any • 2B • Updated • 40 • 1
models active in our lab
-
nightmedia/Qwen3.5-35B-A3B-Holodeck-qx86-hi-mlx
Image-Text-to-Text • 11B • Updated • 24 • 2 -
nightmedia/Qwen3.5-40B-Holodeck-Claude-qx86-hi-mlx
Image-Text-to-Text • 10B • Updated • 8 -
nightmedia/Qwen3.5-9B-OmniCoder-Claude-Polaris-Text-dwq4-mlx
Text Generation • 9B • Updated • 376 • 4 -
nightmedia/Qwen3-Coder-Next-mxfp4-mlx
Text Generation • 80B • Updated • 957 • 6
With a bit of training, smarter
-
nightmedia/gemma-3-12b-it-vl-GLM-4.7-Flash-Polaris-Heretic-Uncensored-Thinking-qx86-hi-mlx
Image-Text-to-Text • 4B • Updated • 323 • 1 -
nightmedia/Gemma-3-27b-it-HERETIC-Gemini-Deep-Reasoning-q8-mlx
Text Generation • 27B • Updated • 55 • 2 -
nightmedia/gemma-3-12b-it-vl-Polaris-Heretic-AIExpert-qx86-hi-mlx
Image-Text-to-Text • 4B • Updated • 12 • 1 -
nightmedia/Gemma-3-27b-it-Gemini-Deep-Reasoning-mxfp4-mlx
Text Generation • 27B • Updated • 30 • 1
Quants that make a difference
-
nightmedia/Qwen3-Next-80B-A3B-Thinking-1M-qx86n-hi-mlx
Text Generation • 80B • Updated • 70 • 3 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-qx86n-mlx
Text Generation • 80B • Updated • 15 • 2 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-qx64-mlx
Text Generation • 80B • Updated • 24 • 4 -
nightmedia/unsloth-GLM-4.5-Air-qx64-mlx
Text Generation • 107B • Updated • 41 • 1
The little engines that could
-
nightmedia/Qwen3-Zero-Coder-Reasoning-0.8B-q8-mlx
Text Generation • 0.2B • Updated • 51 • 1 -
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/Qwen3-4B-Thinking-2507-Esper3.1-qx86-hi-mlx
Text Generation • 1B • Updated • 8 -
nightmedia/Qwen3-VLTO-1.7B-Instruct-qx85x-hi-mlx
Text Generation • 0.4B • Updated • 39 • 1
Unleash the inner experts
-
nightmedia/Qwen3-Next-80B-A3B-Thinking-qx64-hi-mlx
Text Generation • 80B • Updated • 17 • 1 -
nightmedia/Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER-qx4-mlx
Text Generation • 42B • Updated • 708 • 4 -
nightmedia/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-1m-dwq4-mlx
Text Generation • 53B • Updated • 54 • 1 -
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3
Two heads(or more) are better than one
-
nightmedia/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B-qx65-mlx
Text Generation • 27B • Updated • 165 • 1 -
nightmedia/Mistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B-q6-f32-mlx
Text Generation • 24B • Updated • 59 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-1M-qx64n-hi-mlx
Text Generation • 80B • Updated • 12 • 1 -
nightmedia/Qwen3-4B-Jukebox-qx86-hi-mlx
Text Generation • 1B • Updated • 6 • 2
Brainstormed models by DavidAU
-
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/Qwen3-Esper3-Reasoning-CODER-Instruct-12B-Brainstorm20x-q6-mlx
Text Generation • 12B • Updated • 179 • 1 -
nightmedia/Qwen3-TND-Double-Deckard-A-C-11B-220-qx64-hi-mlx
Text Generation • 11B • Updated • 23 • 1 -
nightmedia/Qwen3-VL-12B-Instruct-Brainstorm20x-qx86-hi-mlx
Image-Text-to-Text • Updated • 25 • 1
Emergent behavior
-
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3 -
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/Llama-3.2-PKD-Deckard-Almost-Human-abliterated-uncensored-7B-qx86-hi-mlx
Text Generation • 7B • Updated • 64 • 1 -
nightmedia/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-1m-dwq4-mlx
Text Generation • 53B • Updated • 54 • 1
Trained to be different
-
nightmedia/Mistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B-q6-f32-mlx
Text Generation • 24B • Updated • 59 -
nightmedia/LLama-3.1-128k-Darkest-Planet-Uncensored-16.5B-q5-mlx
Text Generation • 17B • Updated • 53 -
nightmedia/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-q8-mlx
Text Generation • 17B • Updated • 86 -
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3
Coding with Spock
-
nightmedia/Qwen3-ST-TNG-DS9-Voyager-Unhinged-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 55 • 1 -
nightmedia/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B-qx65-mlx
Text Generation • 27B • Updated • 165 • 1 -
nightmedia/Qwen3-4B-Continuum-GGUF
Text Generation • 4B • Updated • 32 -
nightmedia/Qwen3-30B-A3B-Architect7-mxfp4-mlx
Text Generation • 31B • Updated • 3
The world is your oyster—for small pearls
-
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3 -
nightmedia/UIGEN-X-32B-0727-q6-mlx
Text Generation • 33B • Updated • 20 • 1 -
nightmedia/huizimao-gpt-oss-20b-uncensored-mxfp4-q8-hi-mlx
Text Generation • 21B • Updated • 239 • 2 -
nightmedia/VCoder-120b-1.0-qx86-hi-mlx
Text Generation • 117B • Updated • 30 • 3
Some with full context
-
nightmedia/Qwen3-4B-BiasExpert-dwq6-mlx
Text Generation • 1B • Updated • 6 • 2 -
nightmedia/Qwen3-ST-TNG-DS9-Voyager-Unhinged-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 55 • 1 -
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/LFM2-8B-A1B-qx86-hi-mlx
Text Generation • 8B • Updated • 12 • 1
and merges with older models
-
nightmedia/Qwen3.6-35B-A3B-qx86-hi-mlx
Image-Text-to-Text • 11B • Updated • 19 • 1 -
nightmedia/Qwen3.6-35B-A3B-Text-qx64-mlx
Text Generation • 35B • Updated • 49 • 1 -
nightmedia/Qwen3.6-35B-A3B-Holo3-mxfp8-mlx
Image-Text-to-Text • 10B • Updated • 45 -
nightmedia/Qwen3.6-35B-A3B-Architect-Qwopus-mxfp8-mlx
Image-Text-to-Text • 10B • Updated • 60
Same mind, different sizes
-
nightmedia/Qwen3.5-122B-A10B-Text-mxfp4-mlx
Text Generation • 122B • Updated • 1.35k • 10 -
nightmedia/Qwen3.5-35B-A3B-Text-qx64-hi-mlx
Text Generation • 35B • Updated • 89 • 8 -
nightmedia/Qwen3.5-122B-A10B-Text-qx85-mlx
Text Generation • 122B • Updated • 325 • 5 -
nightmedia/Qwen3.5-35B-A3B-Text
Text Generation • 35B • Updated • 27 • 2
models with inspiration
-
nightmedia/Qwen3.5-35B-A3B-Claude-4.6-Opus-Engineer-9e-qx64-hi-mlx
Text Generation • 35B • Updated • 34 • 1 -
nightmedia/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-qx86-hi-mlx
Text Generation • 35B • Updated • 39 • 2 -
nightmedia/Qwen3.5-27B-Architect-Claude-qx86-hi-mlx
Image-Text-to-Text • 7B • Updated • 10 -
nightmedia/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8-mlx
Image-Text-to-Text • 8B • Updated • 307 • 6
Quants created recently.. where time is relative
-
nightmedia/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-qx64-hi-mlx
Text Generation • 27B • Updated • 298 • 12 -
nightmedia/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT-q6-mlx
Image-Text-to-Text • 7B • Updated • 33 -
nightmedia/Qwen3.5-35B-A3B-Text-qx64-hi-mlx
Text Generation • 35B • Updated • 89 • 8 -
nightmedia/Qwen3.5-122B-A10B-Text-mxfp4-mlx
Text Generation • 122B • Updated • 1.35k • 10
Models used in Nightmedia merges
An image is worth a thousand vibes
-
nightmedia/Qwen3-VL-30B-A3B-Instruct-qx86-hi-mlx
Image-Text-to-Text • Updated • 15 • 1 -
nightmedia/Qwen3-VL-12B-Instruct-Brainstorm20x-qx86-hi-mlx
Image-Text-to-Text • Updated • 25 • 1 -
nightmedia/Qwen3-VL-12B-Instruct-BX20-F16-qx86-hi-mlx
Image-Text-to-Text • Updated • 3 • 1 -
nightmedia/UI-Venus-1.5-30B-A3B-qx86-hi-mlx
Image-to-Text • 8B • Updated • 19 • 1
some slower than others
-
nightmedia/UIGEN-X-32B-0727-q6-mlx
Text Generation • 33B • Updated • 20 • 1 -
nightmedia/Qwen3-Zero-Coder-Reasoning-0.8B-q8-mlx
Text Generation • 0.2B • Updated • 51 • 1 -
nightmedia/Qwen3-VLTO-1.7B-Instruct-qx85x-hi-mlx
Text Generation • 0.4B • Updated • 39 • 1 -
nightmedia/unsloth-JanusCoder-8B-qx86x-hi-mlx
Text Generation • 8B • Updated • 24 • 1
small, fast, different, a bit dry
-
nightmedia/LFM2-1.2B-Tool-dwq6-mlx
Text Generation • 0.3B • Updated • 25 -
nightmedia/LFM2-1.2B-Tool-mxfp4-mlx
Text Generation • 0.2B • Updated • 14 -
nightmedia/LFM2-350M-Math-dwq6-mlx
Text Generation • 88.7M • Updated • 12 -
nightmedia/LFM2-1.2B-Extract-dwq6-mlx
Text Generation • 0.3B • Updated • 27 • 1
Models with depth
-
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3 -
nightmedia/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-1m-dwq4-mlx
Text Generation • 53B • Updated • 54 • 1 -
nightmedia/Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER-qx4-mlx
Text Generation • 42B • Updated • 708 • 4 -
nightmedia/Llama-3.2-PKD-Deckard-Almost-Human-abliterated-uncensored-7B-qx86-hi-mlx
Text Generation • 7B • Updated • 64 • 1
brainstorming MoEs by DavidAU
-
nightmedia/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-1m-dwq4-mlx
Text Generation • 53B • Updated • 54 • 1 -
nightmedia/Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER-qx4-mlx
Text Generation • 42B • Updated • 708 • 4 -
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3 -
nightmedia/Qwen3-42B-A3B-YOYO-V5-TOTAL-RECALL-mxfp4-mlx
Text Generation • 42B • Updated • 10
Deckard, the personal assistant
-
nightmedia/Llama-3.2-PKD-Deckard-Almost-Human-abliterated-uncensored-7B-qx86-hi-mlx
Text Generation • 7B • Updated • 64 • 1 -
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/Qwen3-TND-Double-Deckard-A-C-11B-220-qx64-hi-mlx
Text Generation • 11B • Updated • 23 • 1 -
nightmedia/Qwen3.5-4B-ThreeFiddy-mxfp8-mlx
Image-Text-to-Text • 2B • Updated • 6 • 1
96GB and up
-
nightmedia/unsloth-GLM-4.5-Air-qx64-mlx
Text Generation • 107B • Updated • 41 • 1 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-qx86-hi-mlx
Text Generation • 80B • Updated • 18 • 2 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-qx64-mlx
Text Generation • 80B • Updated • 24 • 4 -
nightmedia/LIMI-Air-mxfp4-mlx
Text Generation • 107B • Updated • 12 • 2
Some smarter, and some MoEs
-
nightmedia/huizimao-gpt-oss-20b-uncensored-mxfp4-q4-hi-mlx
Text Generation • 21B • Updated • 166 • 1 -
nightmedia/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-dwq4-mlx
Text Generation • 31B • Updated • 115 • 2 -
nightmedia/ERNIE-4.5-21B-A3B-Thinking-mxfp4-mlx
Text Generation • 22B • Updated • 10 • 1 -
nightmedia/ERNIE-4.5-36B-A3B-Thinking-Brainstorm20x-mxfp4-mlx
Text Generation • 37B • Updated • 22 • 2
All I got.. but eager to code
now with high IQ
and merges with older models
-
nightmedia/Qwen3.6-35B-A3B-qx86-hi-mlx
Image-Text-to-Text • 11B • Updated • 19 • 1 -
nightmedia/Qwen3.6-35B-A3B-Text-qx64-mlx
Text Generation • 35B • Updated • 49 • 1 -
nightmedia/Qwen3.6-35B-A3B-Holo3-mxfp8-mlx
Image-Text-to-Text • 10B • Updated • 45 -
nightmedia/Qwen3.6-35B-A3B-Architect-Qwopus-mxfp8-mlx
Image-Text-to-Text • 10B • Updated • 60
in mxfp4, mxfp8, and Deckard(qx)
-
nightmedia/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx
Image-Text-to-Text • 8B • Updated • 570 • 2 -
nightmedia/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx
Image-Text-to-Text • 8B • Updated • 131 -
nightmedia/gemma-4-E4B-it-mxfp8-mlx
Any-to-Any • 3B • Updated • 35 • 2 -
nightmedia/gemma-4-E4B-it-mxfp4-mlx
Any-to-Any • 2B • Updated • 40 • 1
Same mind, different sizes
-
nightmedia/Qwen3.5-122B-A10B-Text-mxfp4-mlx
Text Generation • 122B • Updated • 1.35k • 10 -
nightmedia/Qwen3.5-35B-A3B-Text-qx64-hi-mlx
Text Generation • 35B • Updated • 89 • 8 -
nightmedia/Qwen3.5-122B-A10B-Text-qx85-mlx
Text Generation • 122B • Updated • 325 • 5 -
nightmedia/Qwen3.5-35B-A3B-Text
Text Generation • 35B • Updated • 27 • 2
models active in our lab
-
nightmedia/Qwen3.5-35B-A3B-Holodeck-qx86-hi-mlx
Image-Text-to-Text • 11B • Updated • 24 • 2 -
nightmedia/Qwen3.5-40B-Holodeck-Claude-qx86-hi-mlx
Image-Text-to-Text • 10B • Updated • 8 -
nightmedia/Qwen3.5-9B-OmniCoder-Claude-Polaris-Text-dwq4-mlx
Text Generation • 9B • Updated • 376 • 4 -
nightmedia/Qwen3-Coder-Next-mxfp4-mlx
Text Generation • 80B • Updated • 957 • 6
models with inspiration
-
nightmedia/Qwen3.5-35B-A3B-Claude-4.6-Opus-Engineer-9e-qx64-hi-mlx
Text Generation • 35B • Updated • 34 • 1 -
nightmedia/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-qx86-hi-mlx
Text Generation • 35B • Updated • 39 • 2 -
nightmedia/Qwen3.5-27B-Architect-Claude-qx86-hi-mlx
Image-Text-to-Text • 7B • Updated • 10 -
nightmedia/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8-mlx
Image-Text-to-Text • 8B • Updated • 307 • 6
With a bit of training, smarter
-
nightmedia/gemma-3-12b-it-vl-GLM-4.7-Flash-Polaris-Heretic-Uncensored-Thinking-qx86-hi-mlx
Image-Text-to-Text • 4B • Updated • 323 • 1 -
nightmedia/Gemma-3-27b-it-HERETIC-Gemini-Deep-Reasoning-q8-mlx
Text Generation • 27B • Updated • 55 • 2 -
nightmedia/gemma-3-12b-it-vl-Polaris-Heretic-AIExpert-qx86-hi-mlx
Image-Text-to-Text • 4B • Updated • 12 • 1 -
nightmedia/Gemma-3-27b-it-Gemini-Deep-Reasoning-mxfp4-mlx
Text Generation • 27B • Updated • 30 • 1
Quants created recently.. where time is relative
-
nightmedia/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-qx64-hi-mlx
Text Generation • 27B • Updated • 298 • 12 -
nightmedia/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT-q6-mlx
Image-Text-to-Text • 7B • Updated • 33 -
nightmedia/Qwen3.5-35B-A3B-Text-qx64-hi-mlx
Text Generation • 35B • Updated • 89 • 8 -
nightmedia/Qwen3.5-122B-A10B-Text-mxfp4-mlx
Text Generation • 122B • Updated • 1.35k • 10
Quants that make a difference
-
nightmedia/Qwen3-Next-80B-A3B-Thinking-1M-qx86n-hi-mlx
Text Generation • 80B • Updated • 70 • 3 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-qx86n-mlx
Text Generation • 80B • Updated • 15 • 2 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-qx64-mlx
Text Generation • 80B • Updated • 24 • 4 -
nightmedia/unsloth-GLM-4.5-Air-qx64-mlx
Text Generation • 107B • Updated • 41 • 1
Models used in Nightmedia merges
The little engines that could
-
nightmedia/Qwen3-Zero-Coder-Reasoning-0.8B-q8-mlx
Text Generation • 0.2B • Updated • 51 • 1 -
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/Qwen3-4B-Thinking-2507-Esper3.1-qx86-hi-mlx
Text Generation • 1B • Updated • 8 -
nightmedia/Qwen3-VLTO-1.7B-Instruct-qx85x-hi-mlx
Text Generation • 0.4B • Updated • 39 • 1
An image is worth a thousand vibes
-
nightmedia/Qwen3-VL-30B-A3B-Instruct-qx86-hi-mlx
Image-Text-to-Text • Updated • 15 • 1 -
nightmedia/Qwen3-VL-12B-Instruct-Brainstorm20x-qx86-hi-mlx
Image-Text-to-Text • Updated • 25 • 1 -
nightmedia/Qwen3-VL-12B-Instruct-BX20-F16-qx86-hi-mlx
Image-Text-to-Text • Updated • 3 • 1 -
nightmedia/UI-Venus-1.5-30B-A3B-qx86-hi-mlx
Image-to-Text • 8B • Updated • 19 • 1
Unleash the inner experts
-
nightmedia/Qwen3-Next-80B-A3B-Thinking-qx64-hi-mlx
Text Generation • 80B • Updated • 17 • 1 -
nightmedia/Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER-qx4-mlx
Text Generation • 42B • Updated • 708 • 4 -
nightmedia/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-1m-dwq4-mlx
Text Generation • 53B • Updated • 54 • 1 -
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3
some slower than others
-
nightmedia/UIGEN-X-32B-0727-q6-mlx
Text Generation • 33B • Updated • 20 • 1 -
nightmedia/Qwen3-Zero-Coder-Reasoning-0.8B-q8-mlx
Text Generation • 0.2B • Updated • 51 • 1 -
nightmedia/Qwen3-VLTO-1.7B-Instruct-qx85x-hi-mlx
Text Generation • 0.4B • Updated • 39 • 1 -
nightmedia/unsloth-JanusCoder-8B-qx86x-hi-mlx
Text Generation • 8B • Updated • 24 • 1
Two heads(or more) are better than one
-
nightmedia/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B-qx65-mlx
Text Generation • 27B • Updated • 165 • 1 -
nightmedia/Mistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B-q6-f32-mlx
Text Generation • 24B • Updated • 59 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-1M-qx64n-hi-mlx
Text Generation • 80B • Updated • 12 • 1 -
nightmedia/Qwen3-4B-Jukebox-qx86-hi-mlx
Text Generation • 1B • Updated • 6 • 2
small, fast, different, a bit dry
-
nightmedia/LFM2-1.2B-Tool-dwq6-mlx
Text Generation • 0.3B • Updated • 25 -
nightmedia/LFM2-1.2B-Tool-mxfp4-mlx
Text Generation • 0.2B • Updated • 14 -
nightmedia/LFM2-350M-Math-dwq6-mlx
Text Generation • 88.7M • Updated • 12 -
nightmedia/LFM2-1.2B-Extract-dwq6-mlx
Text Generation • 0.3B • Updated • 27 • 1
Brainstormed models by DavidAU
-
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/Qwen3-Esper3-Reasoning-CODER-Instruct-12B-Brainstorm20x-q6-mlx
Text Generation • 12B • Updated • 179 • 1 -
nightmedia/Qwen3-TND-Double-Deckard-A-C-11B-220-qx64-hi-mlx
Text Generation • 11B • Updated • 23 • 1 -
nightmedia/Qwen3-VL-12B-Instruct-Brainstorm20x-qx86-hi-mlx
Image-Text-to-Text • Updated • 25 • 1
Models with depth
-
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3 -
nightmedia/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-1m-dwq4-mlx
Text Generation • 53B • Updated • 54 • 1 -
nightmedia/Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER-qx4-mlx
Text Generation • 42B • Updated • 708 • 4 -
nightmedia/Llama-3.2-PKD-Deckard-Almost-Human-abliterated-uncensored-7B-qx86-hi-mlx
Text Generation • 7B • Updated • 64 • 1
Emergent behavior
-
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3 -
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/Llama-3.2-PKD-Deckard-Almost-Human-abliterated-uncensored-7B-qx86-hi-mlx
Text Generation • 7B • Updated • 64 • 1 -
nightmedia/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-1m-dwq4-mlx
Text Generation • 53B • Updated • 54 • 1
brainstorming MoEs by DavidAU
-
nightmedia/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-1m-dwq4-mlx
Text Generation • 53B • Updated • 54 • 1 -
nightmedia/Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER-qx4-mlx
Text Generation • 42B • Updated • 708 • 4 -
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3 -
nightmedia/Qwen3-42B-A3B-YOYO-V5-TOTAL-RECALL-mxfp4-mlx
Text Generation • 42B • Updated • 10
Trained to be different
-
nightmedia/Mistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B-q6-f32-mlx
Text Generation • 24B • Updated • 59 -
nightmedia/LLama-3.1-128k-Darkest-Planet-Uncensored-16.5B-q5-mlx
Text Generation • 17B • Updated • 53 -
nightmedia/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-q8-mlx
Text Generation • 17B • Updated • 86 -
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3
Deckard, the personal assistant
-
nightmedia/Llama-3.2-PKD-Deckard-Almost-Human-abliterated-uncensored-7B-qx86-hi-mlx
Text Generation • 7B • Updated • 64 • 1 -
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/Qwen3-TND-Double-Deckard-A-C-11B-220-qx64-hi-mlx
Text Generation • 11B • Updated • 23 • 1 -
nightmedia/Qwen3.5-4B-ThreeFiddy-mxfp8-mlx
Image-Text-to-Text • 2B • Updated • 6 • 1
Coding with Spock
-
nightmedia/Qwen3-ST-TNG-DS9-Voyager-Unhinged-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 55 • 1 -
nightmedia/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B-qx65-mlx
Text Generation • 27B • Updated • 165 • 1 -
nightmedia/Qwen3-4B-Continuum-GGUF
Text Generation • 4B • Updated • 32 -
nightmedia/Qwen3-30B-A3B-Architect7-mxfp4-mlx
Text Generation • 31B • Updated • 3
96GB and up
-
nightmedia/unsloth-GLM-4.5-Air-qx64-mlx
Text Generation • 107B • Updated • 41 • 1 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-qx86-hi-mlx
Text Generation • 80B • Updated • 18 • 2 -
nightmedia/Qwen3-Next-80B-A3B-Instruct-qx64-mlx
Text Generation • 80B • Updated • 24 • 4 -
nightmedia/LIMI-Air-mxfp4-mlx
Text Generation • 107B • Updated • 12 • 2
The world is your oyster—for small pearls
-
nightmedia/Qwen3-53B-A3B-TOTAL-RECALL-MASTER-CODER-v1.4-q6-mlx
Text Generation • 53B • Updated • 138 • 3 -
nightmedia/UIGEN-X-32B-0727-q6-mlx
Text Generation • 33B • Updated • 20 • 1 -
nightmedia/huizimao-gpt-oss-20b-uncensored-mxfp4-q8-hi-mlx
Text Generation • 21B • Updated • 239 • 2 -
nightmedia/VCoder-120b-1.0-qx86-hi-mlx
Text Generation • 117B • Updated • 30 • 3
Some smarter, and some MoEs
-
nightmedia/huizimao-gpt-oss-20b-uncensored-mxfp4-q4-hi-mlx
Text Generation • 21B • Updated • 166 • 1 -
nightmedia/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-dwq4-mlx
Text Generation • 31B • Updated • 115 • 2 -
nightmedia/ERNIE-4.5-21B-A3B-Thinking-mxfp4-mlx
Text Generation • 22B • Updated • 10 • 1 -
nightmedia/ERNIE-4.5-36B-A3B-Thinking-Brainstorm20x-mxfp4-mlx
Text Generation • 37B • Updated • 22 • 2
Some with full context
-
nightmedia/Qwen3-4B-BiasExpert-dwq6-mlx
Text Generation • 1B • Updated • 6 • 2 -
nightmedia/Qwen3-ST-TNG-DS9-Voyager-Unhinged-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 55 • 1 -
nightmedia/Qwen3-Deckard-6B-qx86-hi-mlx
Text Generation • 6B • Updated • 5 • 1 -
nightmedia/LFM2-8B-A1B-qx86-hi-mlx
Text Generation • 8B • Updated • 12 • 1
All I got.. but eager to code