Cloudflare/clef
Image-Text-to-Text • 27B • Updated • 12.1k • 1.93k
Oblx
OblxDev
AI & ML interests
None yet
Recent Activity
liked a model 7 days ago
Cloudflare/clef liked a model 9 days ago
Reza2kn/Jev-Omni-Q4_K_M-GGUF liked a model 12 days ago
Hikari07jp/MiMo-V2.6-Distill-Qwen-9B-AblitratedOrganizations
None yet
liked a
model 7 days ago
liked a
model 9 days ago
liked a
model 12 days ago
reacted to BoldingBuilds's post with 🔥 12 days ago
Post
364
I tested every uncensored Ternary Bonsai 2 27B on the Hub, all 11 builds from 6 uploaders, including my own. Same prompts, same judge, same GPUs, every file pinned by sha256.
• Best answers: @Hikari07jp and @dealignai (~0.94 answer quality with thinking off)
• Only edit with no measurable MMLU cost: mine (±0.15 pp). Every other edit loses 0.64–2.68 pp, all p < 0.001
• Heretic and Blackfrost still refuse 11–12% of harmful prompts
• Thinking mode at 4,096 tokens: 5–31% of harmful prompts get no answer. PrismML recommends 16,384+, and I'm rerunning at that budget
Full report, charts and model-card checks: BoldingBuilds/bonsai-2-uncensored-shootout
• Best answers: @Hikari07jp and @dealignai (~0.94 answer quality with thinking off)
• Only edit with no measurable MMLU cost: mine (±0.15 pp). Every other edit loses 0.64–2.68 pp, all p < 0.001
• Heretic and Blackfrost still refuse 11–12% of harmful prompts
• Thinking mode at 4,096 tokens: 5–31% of harmful prompts get no answer. PrismML recommends 16,384+, and I'm rerunning at that budget
Full report, charts and model-card checks: BoldingBuilds/bonsai-2-uncensored-shootout
liked 2
models 17 days ago
liked a
model 23 days ago
reacted to DavidAU's post with ❤️ about 1 month ago
Post
12104
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored
This is the first fine tune to exceed 730 "arc-c" ("735": 144 pts higher than Qwen 3.8 27B) AND 880 ARC-E (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and over 718 arc-c in 4 bit.
This version is called TURBO because it drastically reduces thinking tokens (by 1/2 to as high as 1/10), yet maintains output detail and quality.
In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.
This repo contains both "regular" and "MTP" Neo-CODER MAX DI-MATRIX (duel imatrix) GGUF quants.
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
PS: There are 29 additional quant repos as of this writing too, as well NVFP4 and many more as well.
This is one of 10+ Qwen 3.8 27B at or above ARC-C of 717 (all 10 exceed all core benchmarks of Qwen 3.8, 3.6 and 3.5 27B and 35B-A3B versions) - you can see the complete project and some of the training here :
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
This is the first fine tune to exceed 730 "arc-c" ("735": 144 pts higher than Qwen 3.8 27B) AND 880 ARC-E (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and over 718 arc-c in 4 bit.
This version is called TURBO because it drastically reduces thinking tokens (by 1/2 to as high as 1/10), yet maintains output detail and quality.
In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.
This repo contains both "regular" and "MTP" Neo-CODER MAX DI-MATRIX (duel imatrix) GGUF quants.
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
PS: There are 29 additional quant repos as of this writing too, as well NVFP4 and many more as well.
This is one of 10+ Qwen 3.8 27B at or above ARC-C of 717 (all 10 exceed all core benchmarks of Qwen 3.8, 3.6 and 3.5 27B and 35B-A3B versions) - you can see the complete project and some of the training here :
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
- 9 replies
liked a
model about 1 month ago
Anyone tried this to run only on standard PC ram only?
8
#46 opened 3 months ago
by 
gemstonebro
liked 6
models about 2 months ago
anoane/DeepSeek-V4-Flash-0731-exl3-hybrid-2.72bpw
Text Generation • 52B • Updated • 167 • 3
WatchDG/Qwen3.8-27B-ABLITERATED-EXL3-3.75bpw
Image-Text-to-Text • 8B • Updated • 258 • 5
sakamakismile/Huihui-Qwen3.8-27B-abliterated-NVFP4
Text Generation • 27B • Updated • 26.5k • 65
kai-os/Carnice-V3-GGUF
Image-Text-to-Text • 27B • Updated • 1.29k • 24
0xSero/DeepSeek-V4-Flash-0731-REAP
Text Generation • 193B • Updated • 1.15k • 35
Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF
Image-Text-to-Text • 27B • Updated • 69.4k • 254
liked a
dataset 2 months ago
liked 2
models 2 months ago
liked a
Space 2 months ago