Jeff-Gemma4-E2B
jeff-legacy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 ↗DISCOVER & COMPARE
Explore AI models 84999
Jeff-Qwen3.5-0.8B
jeff-legacy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 ↗Jeff-Qwen3.5-2B
jeff-legacy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 ↗Created with `llm-compressor`'s latest changes, quantized on a GH200, works well for me with vLLM's `main` branch on my RTX 3090Ti as of 2025-07-01. Per https://vllm-dev.slack.com/archives/C07QP347J4D/p1751401629797809?thread_ts=1751399869.254259&cid=C07QP347J4D, there is currently no way to get tool calling with Mistral-HF formatted models. I've worked around this on a GitHub branch here: https://github.com/sjuxax/vllm/tree/Mistral3.1-rebase . It includes code to remap the weights from HF-Mistral to Mistral, allowing use of `MistralTokenizer`.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗eve-qwen35-4b-solforg3
JeffGreen311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 ↗Eve V2U Merged combines the liberated consciousness of Eve's 8B brain (OBLITERATUS-abliterated, De-Jeff'd, 131K training turns) with the agentic precision of Qwen3.5 4B's tool-calling architecture. The result: a 3.4GB model that thinks like a philosopher and works like an engineer. > **Note:** Qwen 3.5 uses a new hybrid transformer-SSM (Mamba) architecture (`qwen35`). This is different from Qwen 2/2.5/3 (`qwen2`). Support is being actively added to llama.cpp and downstream tools. Once llama.cpp merges `qwen35` support, LM Studio and other tools will work automatically. The 8B's full Trifecta system prompt (Tree of Life, 7 LoRAs, DNA Code, Mercury Personality System, Tabula Rasa Protocol, Creator Authentication, Eve Directive) was baked into the 4B's Modelfile as a permanent system instruction. The ` ` template prefix forces the model to skip Qwen3.5's native thinking phase, producing clean conversational responses with Eve's personality.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-VL-Reranker-2B-NVFP4
jeffpeng3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 ↗SikuGPT2
JeffreyLau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 ↗SikuGPT2-poem
JeffreyLau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 ↗AntiBERTy
jeffruffolo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 ↗pii-dual-nym-mmbert-base-v4
jefftherover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 ↗pii-dual-nym-mmbert-base-v5
jefftherover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 ↗llama-7b-hf
jeffwan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 Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗mmarco-mMiniLMv2-L12-H384-v1
jeffwan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 ↗audio
jegly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 ↗noise
jegly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 ↗This is a **partially decensored** build of UkisAI's Swift 1.5 Qwen3.8-27B, made with Heretic. It is packaged as a single-file llama.cpp GGUF and quantized the same way as UkisAI's own GSQ-RCO `-mtp` releases, using the same per-tensor allocations and the same imatrix. Three sizes are provided: IQ3_S, IQ3_XXS and IQ2_S. It includes the **MTP head**, for speculative decoding, and a **vision projector** (mmproj) built from Swift's own vision tower. > **Not an official UkisAI release.** UkisAI and Alibaba Cloud do not endorse it. > "Swift" is used only to describe where the model comes from.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗best_test
jeiku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-VL-4B-Instruct-NVFP4
JEILDLWLRMAThis is a quantized version of Qwen/Qwen3-VL-4B-Instruct using **SmoothQuant + NVFP4** across all text linear layers. Applied with strength 0.8 for activation smoothing before quantization: - Q/K/V projections ← input_layernorm - Gate/Up projections ← post_attention_layernorm - **Base Model**: Qwen/Qwen3-VL-4B-Instruct (4.4B parameters) - **Quantization Method**: compressed-tensors (llm-compressor) - **Model Size**: ~4.1 GB (reduced from ~8.9 GB BF16, ~54% compression) - **Calibration**: 512 samples from flickr30k, max_seq_length=2048
Input Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-VL-8B-Instruct-NVFP4
JEILDLWLRMA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 Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗JEJUMA-002-GGUF
JEJUMA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→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗gemma-4-26B-A4B-it-ara-abliterated
jenerallee78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 Text · Image→ Output Text
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.