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。
Explore AI models 85021
CPH-Community-7B
CypherTroopersA compact 7B-model fine-tuned for **Cypherium blockchain operations**, validator support, node configuration, RPC troubleshooting, and general-purpose lightweight reasoning. This model is optimized for **CPU-only inference** using `llama.cpp` and provides fast responses on low-resource servers such as VPS instances (2–6 vCPUs, 8–16GB RAM). - **Base model:** Qwen2-7B - **Fine-tuning:** QLoRA - **Domain:** Cypherium blockchain RPC, node operations, validator troubleshooting - **Format:** GGUF (`Q4_K_M`) - **Intended use:** lightweight on-device assistant for Cypherium node operators
QwerySmith-1.0-Merged
Cyrax321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
trocr-handwritten-cyrillic
cyrillic-trocr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。
Qwen3.6-27B-A2.8B
Cyronius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
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。
Qwen3.8-Flash-Next-131B-A6B-GGUF
CyroniusA 64.8 GB GGUF of Qwen/Qwen3.8-Flash-Next that scores at parity with the full 90 GB quant on tool-calling, GSM8K, and MMLU — 28% smaller, with **zero training and zero transformer surgery**. A 75.4 GB Q4_0 variant of the same cut is also available for older GPUs; see Files. Qwen3.8-Flash-Next carries a 51B-parameter n-gram hash-embedding table (~29% of total weights): 16 independent hash heads, 8 per n-gram type (bigrams / trigrams), injected at layer 1. This model keeps **1 head of 8 per n-gram type** and drops the other 14, exploiting the built-in redundancy of multi-head hashing (each n-gram is looked up several independent ways; a Bloom-filter-style safety margin). Every other tensor is copied **byte-for-byte** from unsloth's UD-Q3_K_XL dynamic quant, so unsloth's imatrix calibration is preserved exactly. The Q4_0 build is **bigger**, not smaller. The n-gram table is what makes this model compact; Q4_0 simply stores every other tensor at more bits than Q3_K_XL does. You are buying throughput with VRAM. On gfx906 that trade is usually worth it — Q4_0 reaches llama.cpp's MMVQ path while K-quants and IQ4_NL fall through to a generic dequant path several times slower.
titler
Cyronius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
Qwen3.8-27B-Int4-AutoRound
CySpiegel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
textnet-base
czczupTextNet is a lightweight and efficient architecture designed specifically for text detection, offering superior performance compared to traditional models like MobileNetV3. With variants **TextNet-T**, **TextNet-S**, and **TextNet-B** (6.8M, 8.0M, and 8.9M parameters respectively), it achieves an excellent balance between accuracy and inference speed. TextNet achieves state-of-the-art results in text detection, outperforming hand-crafted models in both accuracy and speed. Its architecture is highly efficient, making it ideal for GPU-based applications. We first compare TextNet with representative hand-crafted backbones, such as ResNets and VGG16. For a fair comparison, all models are first pre-trained on IC17-MLT [52] and then finetuned on Total-Text. The proposed TextNet models achieve a better trade-off between accuracy and inference speed than previous hand-crafted models by a significant margin. In addition, notably, our TextNet-T, -S, and -B only have 6.8M, 8.0M, and 8.9M parameters respectively, which are more parameter-efficient than ResNets and VGG16. These results demonstrate that TextNet models are effective for text detection on the GPU device.
deepseek-prover-1.5-25
czhang2718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
The encoder half of `Contrastive-LM/CLM-v0.1-8B`, quantised for llama.cpp. CLM is a ranker, not a generator: a frozen Qwen3-8B encoder with last-token pooling feeding two frozen projection heads. This repo is the encoder. The heads are **not** quantised and **not** re-shipped — `clm-serve` already fetches `CLM_v0.1-8B.pt` from the parent repo into `~/.cache/clm/`. Every quantised file has **last-token pooling baked in** (`pooling_type = 3`), so no runtime flag is needed. `token_embd.weight` and `lm_head` are held at 8-bit in all of them. `clm-serve` fetches the heads into `~/.cache/clm/` on first run. See the parent model card for the full API.
TaoMate-H3-3step-ComfyUI
CZMartin22This repository provides a **ComfyUI-compatible conversion** of the official TaoLiveAIGC/TaoMate-H3 step-3000 EMA LoRA adapter for **MiniMax H3 (FL2VA)**. The original weights were released in PEFT / Diffusers format with non-standard key naming. This converted version maps all weights directly to ComfyUI's DiT structure, embeds the required alpha scalar tensors, and casts the weights to `bfloat16` to save VRAM and disk space (~1.24 GB vs original ~2.48 GB). When loaded in ComfyUI, all **208 patches** attach cleanly without missing key warnings.
PartLLM
Czvvd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
legal-gpt2-decoder
D-240357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。
Orpeus_Text_To_Speech
D-Khalid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。
Llama-3.1-8B-Instruct
d-matrix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
Llama3-8b
d-matrix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
e5-small-en-ru
d0rj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
rut5-base-summ
d0rjFinetuned ai-forever/ruT5-base for text and dialogue summarization. - d0rj/samsum-ru - IlyaGusev/gazeta - zjkarina/matreshka - rcp-meetings/rudialogsum_v2 - GEM/wiki_lingua - mlsum > Scheduler, optimizer and trainer states are saved into this repo, so you can use that to continue finetune with your own data with existing gradients.
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
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
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
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
No matching models
Adjust provider, category or input/output filters. New models are added continuously.
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
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.
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.