This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - IT dataset. It achieves the following results on the evaluation set: - Loss: inf - Wer: 0.1710 The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 64 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 5.0 - mixed_precision_training: Native AMP - Transformers 4.16.0.dev0 - Pytorch 1.10.1+cu102 - Datasets 1.17.1.dev0 - Tokenizers 0.11.0

Speech recognition

Input Audio→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Yi-Coder-9B-Chat-Q4_K_M-GGUF

DBigD

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

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Qwen3.8-27B-NVFP4-AutoRound

dbirks

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

Visual QA

Input Text · Image→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Qwen3.8-27B-W4A16-AutoRound

dbirks

An int4 weight-only (W4A16) quantization of Qwen/Qwen3.8-27B, made with Intel AutoRound and packaged in compressed-tensors for vLLM. The weights are int4 and the activations stay BF16, so it runs on any Ampere-or-newer NVIDIA GPU through the Marlin int4 kernel — no Blackwell needed. It's about 19.5 GB on disk, down from roughly 52 GB at BF16. This build is aimed at non-Blackwell GPUs. If you have a Blackwell card (RTX 50-series, B200, DGX Spark), the NVFP4 (W4A4) sibling uses the FP4 tensor cores and will be faster. Accuracy notes are in the Evaluation section below. - **Base model:** `Qwen/Qwen3.8-27B` — a hybrid **GatedDeltaNet (linear-attention) + full-attention** multimodal decoder (64 layers: 48 linear-attn + 16 full-attn) with a vision tower; 262K context. - **Quantization:** int4 **W4A16** (weight-only, group size 128) on the language-decoder `Linear` layers, **except** the two tiny per-layer recurrence-control projections (`in_proj_a`, `in_proj_b`) which stay BF16. - **Kept BF16:** `linear_attn.in_proj_a` / `in_proj_b`, the entire `visual.*` vision tower, the `mtp` head, and `lm_head`. - **Format:** compressed-tensors (`pack-quantized`), auto-detected by vLLM (Marlin int4). - **Quantizer:** Intel AutoRound (arXiv:2309.05516), SignRound block reconstruction.

Visual QA

Input Text · Image→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

bert-base-cased-finetuned-conll03-english

dbmdz

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。

Text analysis

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

bert-base-french-europeana-cased

dbmdz

In this repository the MDZ Digital Library team (dbmdz) at the Bavarian State Library open sources French Europeana BERT models 🎉 We extracted all French texts using the `language` metadata attribute from the Europeana corpus. Based on the metadata information, texts from the 18th - 20th century are mainly included in the training corpus.

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

bert-base-german-cased

dbmdz

In this repository the MDZ Digital Library team (dbmdz) at the Bavarian State Library open sources another German BERT models 🎉 In addition to the recently released German BERT model by deepset we provide another German-language model. The source data for the model consists of a recent Wikipedia dump, EU Bookshop corpus, Open Subtitles, CommonCrawl, ParaCrawl and News Crawl. This results in a dataset with a size of 16GB and 2,350,234,427 tokens.

Fill-mask

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

Monthly input tokens 10 MMonthly output tokens 2 M1 M = 1 million tokens · USD
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

Selection guide & FAQ

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.

Find your ideal AI model.

Explore AI models 84991

Qwen-Image-Bench-GGUF

Qwen2.5-Coder-14B-n8n-Workflow-Generator

pebblo-classifier

GRM-2.6-Plus-0628-MTP-reasoning-i1-GGUF

Qwen3.6-27B-Claude-Opus-Reasoning-MTP-gguf

Qwen3.6-27B-Claude-Opus-Reasoning-UD-Q4_K_RA-XL-gguf

krea-realtime-video

Spark-X2.6-4B-heretic

deep_seek_R1_7B

AST-BirdSet-XCL

AudioProtoPNet-20-BirdSet-XCL

AudioProtoPNet-5-BirdSet-XCL

Bird-MAE-Huge

ConvNeXT-Base-BirdSet-XCL

EfficientNet-B1-BirdSet-XCL

Wav2Vec2-Base-BirdSet-XCL

gpt2-french-small

wav2vec2-xls-r-300m-italian

Yi-Coder-9B-Chat-Q4_K_M-GGUF

Qwen3.8-27B-NVFP4-AutoRound

Qwen3.8-27B-W4A16-AutoRound

bert-base-cased-finetuned-conll03-english

bert-base-french-europeana-cased

bert-base-german-cased

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.