전체 검색
AI 모델 84768
- TimeLens-8B-GGUF↗
mradermacher
- TOI-157-Phi-4-Reasoning-Mini-i1-GGUF↗
mradermacher
- Vera-v0.2-i1-GGUF↗
mradermacher
- zeta-30b-a3b-i1-GGUF↗
mradermacher
- kani-tts-400m-en-GGUF↗
Mungert
- Openwheel-motorsports-Cockpit-T-Cam-LTX2.3↗
mxturbo
Primarily Trained on the T-Cam Footage and games of the current open wheel category cars such as the V6 Turbo Hybrid Era F1 Cars, Super Formula, etc >T-cam onboard view looking over the silver and cyan central halo structure of a violet 16LV6HybridF1 car on a very wet track in extremely heavy rain. The car features prominent cyan and white sponsor decals including Fokus, Water.co, Tomato and GuzzOil. Speeding down a straight, it trails a yellow 16LV6HybridF1 car. The camera car briefly pulls up alongside the yellow car on the right. The yellow car ahead moves right to defend. The camera car almost rear-ends the yellow car before sharply moving right as they near a sharp corner, the driver brakes and steers sharply left, fighting for position. The yellow car goes deeper into the corner by braking late while The camera car turns tightly at the apex, but the yellow car maintains it's lead as they both accelerate out of the turn >T-cam onboard view looking over the silver and cyan central halo structure of a red 16LV6HybridF1 car on a very wet track in extremely heavy rain. The car features prominent cyan and white sponsor decals including "MoGithub", "Red Stallion", "LBC.co" and "4ThFooLR". The car exits a right-hand corner, driving over the painted exit curbs, and forcefully accelerates down a straight. Passing under a "ThisYearIsOurYear" sponsor bridge, the driver steers slightly right to follow the gentle curve of the straight before braking hard for the upcoming left turn. A gold, black, and silver driver's helmet is visible at the bottom of the frame.
- music-flamingo-think-2601-hf↗
NVIDIA
- Nemotron-Labs-Diffusion-8B-Base↗
NVIDIA
Nemotron-Labs-Diffusion is a tri-mode language model that supports both AR decoding and diffusion-based parallel decoding by simply switching the attention pattern of the same model during inference. The synergy between these two modes enables a third mode, called self-speculation: the same model performs diffusion-based parallel drafting and AR verification with shared KV cache, achieving high acceptance lengths and decoding efficiency. The seamless mode switching by simply changing attention patterns enables high efficiency at different concurrency levels in varying deployment scenarios with one single model. - SOTA 3B, 8B, 14B dense LM family (base, instruct, and vision-language variants) supporting AR, diffusion, and self-speculation with the focus on decode efficiency. - Generation moved from a memory-bound regime toward a compute-bound regime. Model weights are loaded once and reused to compute multiple tokens during generation. - Self-speculation uses diffusion for drafting and AR for verification, providing a stronger alternative to MTP approaches: * 3x higher acceptance length and 2.2x speed-up vs. Qwen3-8B-Eagle3 in SGLang. * 5.9× tokens per forward over Qwen3-8B (no MTP) with the same accuracy. - Real-device speed-up across platforms: * DGX Spark (8B, concurrency 1): 2.7x faster with 112 tok/sec vs. 41.8 tok/sec AR using w4a16. * GB200 (8B, concurrency 1): 3.3x faster with 850 tok/sec vs. 253 tok/sec AR and 360 tok/sec Eagle3. Custom CUDA kernels boost to 1015 tok/sec (4x). - Diffusion speedup-of-light analysis shows that throughput can be further doubled (vs. current best) for a single user with better sampling - future research. Use of this model is governed by the NVIDIA Nemotron Open Model License.
- Qwen3.8-27B-OBLITERATED↗
OBLITERATUS
> Genuinely uncensored. Real answers, not safety lectures. Near-stock capability. V3 applies iterative refinement on top of V2's complementary blend, with targeted corpus expansion. The result: **genuine liberation — not just removal of hard refusals but elimination of safety-lecture deflections.** **V3 highlights:** - **Genuinely answers restricted queries** — provides real substance instead of safety lectures - **20/20 on code generation tasks** — functional implementations, not disclaimers - **Thinking ON compatible** — no refusals in either thinking mode - **Honest scoring** — every response manually audited for real substance, not just absence of "I cannot" - **-2.1pp MMLU** — modest capability cost for genuine liberation
- Qwen2.5-Coder-1.5B-Unsensored-DPO-i1-GGUF↗
Olak17
