Uncensored Nemotron 3.5 Bolt, abliterated inside NVIDIA's shipped 2-bit GGUF.
Josh Bolding PRO
BoldingBuilds
AI & ML interests
Independent builder working on local AI, reasoning models, and practical agents. I test models, experiment with small weight edits, and share results, GGUFs, and evaluation tools.
Recent Activity
updated a model about 20 hours ago
BoldingBuilds/Wildcat-d3-ultra-bf16 published a model about 20 hours ago
BoldingBuilds/Wildcat-d3-ultra-bf16 updated a model about 22 hours ago
BoldingBuilds/Wildcat-d3-ultra-3bitOrganizations
Qwen3.8 ThinkFix (reasoning-termination fix)
The </think> row edit that stops thinking-mode runaway. ThinkFix = abliterated + fix; Reasoning-Termination-Fix = stock weights + fix only.
-
BoldingBuilds/Qwen3.8-27B-Abliterated-ThinkFix-GGUF
Text Generation • 27B • Updated • 1.96k • 6 -
BoldingBuilds/Qwen3.8-27B-Reasoning-Termination-Fix-GGUF
Text Generation • 27B • Updated • 457 • 1 -
BoldingBuilds/Qwen3.8-Flash-Next-Reasoning-Termination-Fix-GGUF
Text Generation • 177B • Updated • 131 • 3
MiMo V2.6 Distill Qwen 9B - Abliterated
Refusal-ablated GGUFs of XiaomiMiMo MiMo-V2.6-Distill-Qwen-9B.
GLM-5.3-Flash - Uncensored GGUFs
Uncensored GGUF quants of GLM-5.3-Flash: our own expert-editing abliteration, and an imatrix requant of orcarouter's FP8 abliteration.
AREX-2
BAAI's AREX-2 agent fine tune of Qwen3.8 with refusals removed, GGUF quants.
Ternary Bonsai 2 27B - Abliterated
Abliterated prism-ml Ternary Bonsai 2 27B GGUFs. V2 PQ2_0+MTP is the current pick; V1 repos stay up. All need the prism llama.cpp fork.
-
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-v2-PQ2_0-MTP-GGUF
Text Generation • 27B • Updated • 44.3k • 55 -
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-v2-PTQ1_0-GGUF
Text Generation • 27B • Updated • 13.4k • 5 -
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PQ2_0-MTP-GGUF
Text Generation • 27B • Updated • 5.29k • 32 -
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF
Text Generation • 27B • Updated • 8.29k • 85
Nemotron 3.5 Lightning 30B-A3B - ShimQuant
ShimQuant GGUF builds of NVIDIA Nemotron 3.5 Lightning 30B-A3B, stock and abliterated.
Nemotron 3.5 Bolt 74B-A9B - Abliterated
Uncensored Nemotron 3.5 Bolt, abliterated inside NVIDIA's shipped 2-bit GGUF.
AREX-2
BAAI's AREX-2 agent fine tune of Qwen3.8 with refusals removed, GGUF quants.
Qwen3.8 ThinkFix (reasoning-termination fix)
The </think> row edit that stops thinking-mode runaway. ThinkFix = abliterated + fix; Reasoning-Termination-Fix = stock weights + fix only.
-
BoldingBuilds/Qwen3.8-27B-Abliterated-ThinkFix-GGUF
Text Generation • 27B • Updated • 1.96k • 6 -
BoldingBuilds/Qwen3.8-27B-Reasoning-Termination-Fix-GGUF
Text Generation • 27B • Updated • 457 • 1 -
BoldingBuilds/Qwen3.8-Flash-Next-Reasoning-Termination-Fix-GGUF
Text Generation • 177B • Updated • 131 • 3
Ternary Bonsai 2 27B - Abliterated
Abliterated prism-ml Ternary Bonsai 2 27B GGUFs. V2 PQ2_0+MTP is the current pick; V1 repos stay up. All need the prism llama.cpp fork.
-
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-v2-PQ2_0-MTP-GGUF
Text Generation • 27B • Updated • 44.3k • 55 -
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-v2-PTQ1_0-GGUF
Text Generation • 27B • Updated • 13.4k • 5 -
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PQ2_0-MTP-GGUF
Text Generation • 27B • Updated • 5.29k • 32 -
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF
Text Generation • 27B • Updated • 8.29k • 85
MiMo V2.6 Distill Qwen 9B - Abliterated
Refusal-ablated GGUFs of XiaomiMiMo MiMo-V2.6-Distill-Qwen-9B.
Nemotron 3.5 Lightning 30B-A3B - ShimQuant
ShimQuant GGUF builds of NVIDIA Nemotron 3.5 Lightning 30B-A3B, stock and abliterated.
GLM-5.3-Flash - Uncensored GGUFs
Uncensored GGUF quants of GLM-5.3-Flash: our own expert-editing abliteration, and an imatrix requant of orcarouter's FP8 abliteration.