Ming-flash-omni-2.0
Jonathan1909基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 85001
Qwen3.8-27B-Uncensored
JonathanColettiThese 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.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-Uncensored-GGUF
JonathanColettiUncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been **substantially reduced**, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Method - Whats here - Overview - Files - Perplexity - Baseline against the unmodified base model - How the baseline was measured - Importance matrix - Building other low bit quants yourself - Third party quants - Usage - ComfyUI - llama cpp - Verification - Measured behaviour - How to read these - Caveats that matter - Requirements - Limitations - License - Speculative decoding, measured on this model - IQ2_M
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗face-parsing
jonathandinu> ONNX model for web inference contributed by Xenova. Exhaustive list of labels can be extracted from config.json. Since p5.js uses an animation loop abstraction, we need to take care loading the model and making predictions.
Input Image→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗mos-mamba-18x130m-trainer-dgx-pile
jonathanjordan21基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗jonawhisper-gec-t5-small-onnx
JonaWhisper基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗airoboros-70b-3.3
jondurbinThis model uses the llama-3-instruct prompt template, and is provided in the tokenizer config. You can use the `apply_chat_template` method to accurate format prompts, e.g.: BEGININPUT BEGINCONTEXT [key0: value0] [key1: value1] ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗airoboros-dpo-70b-3.3
jondurbinAnother experimental model, tuned primarily from synthetic data generated by airoboros, plus an additional tuning phase with various DPO datasets. This model uses the llama-3-instruct prompt template, and is provided in the tokenizer config. You can use the `apply_chat_template` method to accurate format prompts, e.g.: BEGININPUT BEGINCONTEXT [key0: value0] [key1: value1] ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗bagel-8b-v1.0
jondurbinThis is a fine-tune of llama-3-8b using the bagel dataset, but instead of 4 prompt formats it's standardized on a single format - llama-3 instruct. There are many data sources used in the bagel models. See https://github.com/jondurbin/bagel for more information. __*Only train splits are used, and a decontamination by cosine similarity is performed at the end as a sanity check against common benchmarks. If you don't know the difference between train and test, please learn.*__
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗bagel-dpo-34b-v0.2
jondurbinThis version also includes the toxic DPO dataset, and should have less censorship than it's counterparts. You may want to use a system prompt like: 1) For this model, create an account in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental. 2) After you created your account update your billing and navigate to the deploy page. 3) Select the following - GPU Type: A6000 - GPU Quantity: 2 - Category: Creator - Image: Jon Durbin - Coupon Code: JonDurbin 4) Deploy the VM! 5) Navigate to 'Running Instances' to retrieve instructions to login to the VM 6) Once inside the VM, open the terminal and run `volume=$PWD/data` 7) Run `model=jondurbin/bagel-dpo-34b-v0.2` 8) `sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model` 9) The model will take some time to load... 10) Once loaded the model will be available on port 8080 *Yes, you will see benchmark names in the list, but this only uses the train splits, and a decontamination by cosine similarity is performed at the end as a sanity check*
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗bagel-dpo-34b-v0.5
jondurbinThis is a fine-tune of the updated yi-34b-200k with better long-context support, which underwent additional tuning via direct preference optimization (DPO). There are many data sources used in the bagel models. See https://github.com/jondurbin/bagel for more information. __*Only train splits are used, and a decontamination by cosine similarity is performed at the end as a sanity check against common benchmarks. If you don't know the difference between train and test, please learn.*__
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗electra-small-nordic
jonfdThis model was pretrained on the following corpora: * The Icelandic Gigaword Corpus (IGC) * The Icelandic Common Crawl Corpus (IC3) * The Icelandic Crawled Corpus (ICC) * The Multilingual Colossal Clean Crawled Corpus (mC4) - Icelandic, Norwegian, Swedish and Danish text obtained from .is, .no, .se and .dk domains, respectively The total size of the corpus after document-level deduplication and filtering was 14.82B tokens, split equally between the four languages. The model was trained using a WordPiece tokenizer with a vocabulary size of 96,105 for one million steps with a batch size of 256, and otherwise with default settings. This project was funded by the Language Technology Programme for Icelandic 2019-2023. The programme, which is managed and coordinated by Almannarómur, is funded by the Icelandic Ministry of Education, Science and Culture.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MolGPT_pretrained-by-ZINC15
jonghyunlee1993基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.5-35B-A3B-heretic-GGUF
Jongsim基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗NSFWMaster
Jonjew基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗PussyDiffusion
Jonjew基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.