> [!NOTE] > **WARNING:** Although this model has undergone safety and value alignment, it may still occasionally generate unintended or undesired outputs. > > **Sampling Parameters:** For optimal performance, we recommend using temperatures close to zero (0 - 0.2). Additionally, we advise against using any type of repetition penalty, as from our experience, it negatively impacts instructed model's responses. The Salamandra-7b-instruct model is an instructed variant of a context-extended base Salamandra-7b model, which was pre-trained from scratch on 9.83 trillion tokens of carefully curated data spanning 35 European languages (including code). This instructed version is optimized to follow user prompts and engage in dialogue. It supports a broad range of languages (e.g. Spanish, Catalan, Basque, English, etc.) and is capable of text generation, translation, summarization, and question-answering in these languages. This version has also gone through a preliminary alignment phase for helpfulness and safety with synthetically generated preference pairs. The model has been made openly available under the Apache 2.0 license for the benefit of society. Through this open release, ALIA seeks to accelerate scientific progress and innovation by enabling the scientific community and society at large to use, study, evaluate, adapt, further develop, and build upon the model. This open approach promotes collaboration, transparency, and the responsible development of artificial intelligence, helping to advance knowledge, drive technological innovation, and contribute to the public interest. The post-training datasets are publicly available in ALIA-SFT, ALIA-SFT-tools, ALIA-DPO-helpulness, and ALIA-DPO-safety.
Explore AI models 84991
salamandraTA-2b-instruct
BSC-LT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
salamandraTA-7b-instruct
BSC-LT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。
vocos-mel-22khz
BSC-LT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
bsc-bio-ehr-es-carmen-anon
BSC-NLP4BIA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
bsc-bio-ehr-es-meddocan
BSC-NLP4BIA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
gred-cozmo
bsu-slim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
Illustrious-XL-v2.0-GGUF
btaskel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
noobai-XL-Vpred-1.0-GGUF
btaskel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。
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
Tifa-DeepsexV2-7b-MGRPO-GGUF
btaskel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
Muse-Glimmer-30B-GPTQ-4bit
btbtyler09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
Qwen3.6-27B-GPTQ-4bit
btbtyler09GPTQ 4-bit quantization of Qwen/Qwen3.6-27B, a 27B-parameter dense multimodal model. Uses **FOEM** (First-Order Error Matters, AAAI 2026) for outlier-aware error compensation, enabling pure 4-bit quantization without per-module FP16 exclusions. Includes the full vision encoder and MTP (Multi-Token Prediction) module for image understanding and speculative decoding support. - **Architecture**: Qwen3_5ForConditionalGeneration (multimodal: text + vision; dense sibling of `qwen3_5_moe`) - **Total parameters**: ~27B - **Layers**: 64 (48 linear-attention + 16 full-attention, repeating 3:1 pattern) - **Hidden size**: 5120, intermediate size: 17408 (dense MLP — no MoE) - **Context length**: 262,144 tokens - **Vision encoder**: 27-block ViT, BF16 (333 tensors) - **MTP module**: 1-layer speculative decoding head, BF16 (15 tensors)
Qwen3.6-35B-A3B-GPTQ-4bit
btbtyler09GPTQ 4-bit quantization of Qwen/Qwen3.6-35B-A3B, a 35B-parameter Mixture-of-Experts (MoE) multimodal model with 3B activated parameters per token. Includes full vision encoder and MTP (Multi-Token Prediction) module for image understanding and speculative decoding support. All 30,720 MoE expert modules (256 experts x 3 projections x 40 layers) are quantized to INT4 using GPTQ. Non-expert modules (including the full vision encoder and MTP module) remain at BF16/FP16 for quality preservation.
Qwen3.6-35B-A3B-GPTQ-8bit
btbtyler09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-GPTQ-4bit
btbtyler09GPTQ 4-bit quantization of Qwen/Qwen3.8-27B, a 27B-parameter dense multimodal model. Uses **FOEM** (First-Order Error Matters, AAAI 2026) for outlier-aware error compensation, enabling pure 4-bit quantization without per-module FP16 exclusions — this checkpoint lands at **+0.81% perplexity** over BF16. Includes the full vision encoder and MTP (Multi-Token Prediction) module for image understanding and speculative decoding support. All quantizable Linear modules in the text decoder are quantized to INT4 using GPTQ + FOEM. The vision encoder, MTP module, norms, embeddings, and LM head remain at BF16/FP16 for quality preservation.
Qwen3.8-27B-GPTQ-8bit
btbtyler09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-Flash-Next-GPTQ-4bit
btbtyler09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-Coder-Next-GPTQ-4bit
btbtyler09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。
transcoda-59M-zeroshot-v1
btrkeks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.