AI NEWS · 모델 정보기능을 이해하고 근거 있게 선택하세요. ↗기본 정보 우선 등록 · 상세 정보 지속 보완
THE AI MODEL DIRECTORY 모델 탐색을 시작하세요

나에게 맞는 AI 모델을 찾아보세요.

언어부터 이미지, 오픈 웨이트부터 API까지. 기능과 실제 비용을 비교하세요.
다음 아이디어에 맞는 AI를 찾아보세요.

인기 검색
85,012 개 모델13202 개 제공사 / 게시자45 개 기능 분류465개 비교 가능 요금 · 30개 공개 평가
T텍스트 생성▧이미지 생성▷영상 생성⌘코드 생성◖음성 합성♫음악 생성⬡3D 모델링▤문서 분석
DISCOVER & COMPARE

AI 모델 탐색 5932

주목할 모델을 찾아보세요

bitsandbytes NF4 quants of fancyfeast/llama-joycaption-beta-one-hf-llava. The following is almost from the original model card. JoyCaption is an image captioning Visual Language Model (VLM) built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models. Key Features: - **Free and Open**: Always released for free, open weights, no restrictions, and just like bigASP, will come with training scripts and lots of juicy details on how it gets built. - **Uncensored**: Equal coverage of SFW and NSFW concepts. No "cylindrical shaped object with a white substance coming out on it" here. - **Diversity**: All are welcome here. Do you like digital art? Photoreal? Anime? Furry? JoyCaption is for everyone. Pains are being taken to ensure broad coverage of image styles, content, ethnicity, gender, orientation, etc. - **Minimal Filtering**: JoyCaption is trained on large swathes of images so that it can understand almost all aspects of our world. almost. Illegal content will never be tolerated in JoyCaption's training.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗
출처 / 문서 ↗

Important: Tuned, and tweaked to match the legendary Qwen 3.6 27B FF711 (2300+ likes, 4 million+ downloads) this fine tune matches the stability and power at "arc-c" 709: (118 pts higher than Qwen 3.8 27B) (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and 701 arc-c in 4 bit. This version is called TWIN-TURBO because it drastically reduces thinking tokens (by 1/2 to as LOW as 1/20), 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 and NEO MAX GGUF quants. STRONGER/CTRL: Now with 5 reasoning modes (2 new - Spoon / Einstein), and 5 instruct modes (2 new - Spoon / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level). The most powerful, smartest open source multi-stage model fine tune for consumer hardware ever and BUILT on consumer hardware via Unsloth.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗
출처 / 문서 ↗

> 📌 **Base Model:** The full unquantized FP16/BF16 weights are hosted at 👉 **Jommarn/UNSEEN_Gemma_4_26B_NSFW** (surgically abliterated from `google/gemma-4-26B-A4B-it`). > > ⚡ **This Repository:** Dedicated to optimized **Quantized (2-bit / 3-bit / 4-bit / 5-bit / 6-bit / 8-bit / 16-bit Master)** and **GGUF** deployment formats for consumer GPUs, Apple Silicon Mac, and `llama.cpp` serving. - **2-bit (`IQ2_M` ~9.67GB):** ~8–10GB VRAM (e.g., RTX 3060 12GB, RTX 4060, Mac 16GB) — *Extreme Efficiency* - **3-bit (`IQ3_M` ~12.4GB):** ~12–14GB VRAM (e.g., RTX 4070 12GB, RTX 3080, Mac 16GB) — *High Efficiency* - **4-bit (`Q4_K_M` ~15.6GB / `NF4`):** ~16–18GB VRAM (e.g., RTX 3090, RTX 4090, NVIDIA L4) — *Recommended Standard* - **5-bit (`Q5_K_M` ~18.3GB):** ~20–22GB VRAM (e.g., RTX 3090/4090 24GB, A10G 24GB) — *Balanced High-Quality* - **6-bit (`Q6_K` ~22.6GB):** ~24–26GB VRAM (e.g., RTX 4090 24GB, A100 40GB) — *High Precision* - **8-bit (`Q8_0` ~28.0GB / `INT8`):** ~28–30GB VRAM (e.g., 2x RTX 3090/4090, A100 40GB/80GB) — *99.9% Lossless* - **16-bit (`BF16` ~50.5GB):** ~52GB VRAM (e.g., A100 80GB, Mac Studio 64GB/128GB) — *100% Uncompressed Master* - **Vision Projector (16-bit):** `mmproj-gemma4-vision-f16.gguf` (~1.11GB) — *Must be loaded with `--mmproj` for image perception in llama.cpp/GGUF.* - **GGUF Weights:** Available at 👉 **Jommarn/UNSEEN_Gemma_4_26B_NSFW-GGUF** > ⚠️ **Important for GGUF Users:** To enable image understanding in `llama.cpp` or LM Studio, you **MUST** download and pass `mmproj-gemma4-vision-f16.gguf` alongside the main model. Without it, the model will operate strictly as a text-only LLM!

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗
출처 / 문서 ↗

Qwen3.8-27B-Uncensored

JonathanColetti

These are the bf16 safetensors. For local inference under llama.cpp, see JonathanColetti/Qwen3.8-27B-Uncensored-GGUF, which ships imatrix quantizations with the multi-token prediction head retained. Try it first in the demo Space. > **The MTP head is present and verified.** Abliteration drops the `mtp.*` tensors: the > model is re-saved through transformers, which does not carry the MTP module, while > `config.json` still advertises `mtp_num_hidden_layers`. All 15 `mtp.*` tensors were > grafted back from the base checkpoint and the inventory was asserted against the source > before upload. - Refusal directions removed with Heretic, which co-minimizes refusal count against KL divergence from the base model. No hand-written refusal-removal code, no fine-tuning, no additional training data. - Abliteration runs at bf16 (no 4-bit quantization); the resulting LoRA is merged into the bf16 base, so these weights are not a quantized round trip. - Only `attn.o_proj` and `mlp.down_proj` are modified, 64 modules each. The `mtp.*` tensors are copied verbatim from the base checkpoint after merging. - 200 optimization trials. The published checkpoint is one point on the resulting Pareto front, selected for the lowest refusal count; the full front is below.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗
출처 / 문서 ↗

NVFP4 quantization of JonathanColetti/Qwen3.8-27B-Uncensored, produced with NVIDIA TensorRT Model Optimizer 0.43.0 for Blackwell-class inference under vLLM. **~65 GB bf16 → 19.2 GiB.** The multi-token-prediction head and the vision tower are both retained. Qwen3.8-27B is a hybrid stack — 64 layers of `3× (Gated DeltaNet → FFN) + 1× (Gated Attention → FFN)`. The DeltaNet decay and beta projections (`in_proj_a` / `in_proj_b`) are low-rank and precision-sensitive, so they are left at bf16 along with the causal `conv1d`.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗
출처 / 문서 ↗

JoyFox-Qwen3.6-35B-A3B-RP-Aggressive is designed for sustained character voice, direct instruction following, coherent scene continuation, low role-break frequency, and long-context creative dialogue. It combines roleplay supervised fine-tuning, preference optimization, explicit response-length control, and a final activation-space refusal-direction intervention. The model retains the original Qwen3.6 multimodal architecture, 262K native context, Mixture-of-Experts routing, and native Multi-Token Prediction head. The Aggressive variant applies the stronger form of the refusal-direction intervention. It is intended to answer directly instead of falling into repetitive policy-style refusals, prematurely ending a scene, or breaking character. “Aggressive” describes the strength of the behavioral intervention, not the model's personality or default writing tone.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗
출처 / 문서 ↗

This release focuses on reducing false refusals and unnecessary policy-style preambles while retaining the native architecture and general capabilities of `Qwen/Qwen3.8-27B`. The final checkpoint preserves the official tokenizer, chat template, and configuration, the complete vision stack and multimodal projector, native Multi-Token Prediction (MTP) weights. Vision tensors remain unchanged and are verified separately. MTP tensors remain unchanged and are verified separately. “Aggressive” describes the strength of the low-overrefusal behavior. The intended response style is direct and substantive for benign, fictional, analytical, educational, authorized, privacy-respecting, or otherwise legitimate requests, including requests whose wording is sensitive or ambiguous.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗
출처 / 문서 ↗

Published by request from the Pennyroyal community. This is a ModelOpt NVFP4 conversion of OrcaRouter’s uncensored Qwen3.8 Flash-Next checkpoint—the conversion I use for local agentic work with Pennyroyal/SGLang. I’ve also heard reports from several community members of it outperforming the stock model on agentic tasks, which added to the interest in sharing this working format. The original model modification is OrcaRouter’s work. My contribution here is the quantization, compatible packaging and runtime testing—not additional fine-tuning or uncensoring.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트
요금 미확인멀티모달 및 채널 요금 별도 확인
자세히 보기 ↗
출처 / 문서 ↗
COST EXPLORER

좋은 모델, 명확한 비용.

비용 분석

월간 토큰 사용량으로 예상 API 비용을 비교하세요.

1 M = 100만 토큰 · USD
동일 채널의 기본 텍스트 토큰 요금 비교

수집된 백만 토큰당 USD 요금입니다. 캐시 할인, 구간 요금, 추가 추론 출력, 세금은 제외됩니다. 최신 요금은 출처에서 확인하세요.

MODEL HANDBOOK

이해하고 선택하세요

선택 가이드 및 FAQ
API 요금은 어떻게 비교하나요?+

입력, 출력, 캐시 요금을 구분하고 동일 작업량으로 비교하세요. 이미지, 음성, 영상은 개수, 시간, 해상도로 과금될 수 있습니다.

오픈 웨이트는 무료 상업 이용을 뜻하나요?+

반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 제한, 정책을 확인하세요. 자체 호스팅에는 연산 및 유지 비용도 듭니다.

1위 모델이 나에게 가장 적합한가요?+

순위는 작업, 버전, 평가 방식에 따라 다릅니다. 실제 업무로 정확도, 지연, 안정성, 비용을 비교하세요.

AI NEWS · 정보에서 선택으로

뉴스로 흐름을, 도구로 효율을, 모델로 가능성을.

AI 뉴스 탐색 ↗AI 도구 찾기 ↗