From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.
All quants made using imatrix option with dataset from here Run them directly with llama.cpp, or any other llama.cpp based project This model has vision capabilities, more details here: https://github.com/ggml-org/llama.cpp/pull/12344
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。
All quants made using imatrix option with dataset from here Run them directly with llama.cpp, or any other llama.cpp based project Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
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。
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。
This model has vision capabilities, more details here: https://github.com/ggml-org/llama.cpp/pull/12344 Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
*ONLY* Q4_0 is expected to be better, but figured while I'm at it I might as well make others to see what happens? gemma-3-27b-it-qat-Q4_0.gguf | Q4_0 | 15.62GB | Should be improved due to QAT, offers online repacking for ARM and AVX CPU inference. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
All quants made using imatrix option with dataset from here Run them directly with llama.cpp, or any other llama.cpp based project This model has vision capabilities, more details here: https://github.com/ggml-org/llama.cpp/pull/12344
*ONLY* Q4_0 is expected to be better, but figured while I'm at it I might as well make others to see what happens? gemma-3-4b-it-qat-Q4_0.gguf | Q4_0 | 2.37GB | false | Should be improved due to QAT, offers online repacking for ARM and AVX CPU inference. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
No chat template specified so default is used. This may be incorrect, check original model card for details. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
No chat template specified so default is used. This may be incorrect, check original model card for details. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
All quants made using imatrix option with dataset from here - llama.cpp - ramalama - LM Studio - koboldcpp - Jan AI - Text Generation Web UI - LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers.
All quants made using imatrix option with dataset from here - llama.cpp - ramalama - LM Studio - koboldcpp - Jan AI - Text Generation Web UI - LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers.
All quants made using imatrix option with dataset from here - llama.cpp - ramalama - LM Studio - koboldcpp - Jan AI - Text Generation Web UI - LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers.
All quants made using imatrix option with dataset from here - llama.cpp - ramalama - LM Studio - koboldcpp - Jan AI - Text Generation Web UI - LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers.
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: You can either specify a new local-dir (google_medgemma-27b-it-Q8_0) or download them all in place (./)
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: You can either specify a new local-dir (google_medgemma-4b-it-Q8_0) or download them all in place (./)
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。
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
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons on the original pull request To check which one would work best for your ARM chip, you can check AArch64 SoC features(thanks EloyOn!). Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
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
Adjust provider, category or input/output filters. New models are added continuously.
Adjust monthly token usage to compare estimated API costs.
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
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.
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.
