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 ↗DISCOVER & COMPARE
Explore AI models 84999
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 ↗Qolda_GGUF
issai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 ↗Qwen3.5-4B-Kazakh
issai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 · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.5-9B-Kazakh
issai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 · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
ISTA-DASLab**Non-uniform GGUF quantizations** of a 763B-parameter, 384-expert MoE, produced with **GSQ** and **RCO**. > **Update, October 27, 2026.** The files now use llama.cpp's own DeepSeek-V4.1 layout and load in llama.cpp b11870 or newer, including images. > - **Downloaded the earlier files?** You do not need to download the model again. Run convert_ds41_upstream.py on your model folder: it rewrites the files locally into exactly the current ones and fetches only 80 KB. See Updating an existing download. > - **New download?** The shared Engram file is shard 6 of every build, so link it once per build you use (` ` is `IQ1_M`, `IQ2_XXS` or `IQ2_XS`; see llama.cpp): > > This repository provides GGUF quantizations of **DeepSeek-V4.1-Flash-1017** at three sizes: **IQ1_M (1.75 bits per weight), IQ2_XXS (2.00) and IQ2_XS (2.25)**. In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗gemma-3-12b-it-GPTQ-4b-128g
ISTA-DASLab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 ↗gemma-3-27b-it-GPTQ-4b-128g
ISTA-DASLabThis model was obtained by quantizing the weights of gemma-3-27b-it to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights of the linear operators within `language_model` transformers blocks are quantized. Vision model and multimodal projection are kept in original precision. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization. Model checkpoint is saved in compressed_tensors format.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗gemma-3-4b-it-GPTQ-4b-128g
ISTA-DASLab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 · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Kimi-K2.5-P48NVFP4-MoESQ
ISTA-DASLab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 ↗Kimi-K3-P48NVFP4-MoESQ
ISTA-DASLab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-3.1-8B-Instruct-GGUF
ISTA-DASLab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 ↗This model was obtained by quantizing the weights of Mistral-Small-3.1-24B-Instruct-2503 to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights of the linear operators within `language_model` transformers blocks are quantized. Vision model and multimodal projection are kept in original precision. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization. Model checkpoint is saved in compressed_tensors format.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3-30B-A3B-P48NVFP4-MoESQ
ISTA-DASLab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 ↗Qwen3.5-4B-GGUF-GSQ
ISTA-DASLab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 ↗Qwen3.6-35B-A3B-2Bit-GSQ
ISTA-DASLab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 · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-3Bit-GSQ
ISTA-DASLab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 · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-GSQ-RCO-GGUF
ISTA-DASLab.json, run python tools/make_plots.py tools/results/ .json then paste the printed Markdown table into "Results". The header (banner + badges) is shared across all releases. NB: the YAML block must remain the very first bytes of the file (HF requirement). --> **Non-uniform GGUF quantizations** produced with **GSQ** and **RCO**, with a vision projector for multimodal use. This repository provides GGUF quantizations of **Qwen3.8-27B** at four sizes, together with the model's vision projector (`mmproj`) for multimodal use. In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF and run unmodified in `llama.cpp`, Ollama, and LM Studio.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-NVFP4-prefiller
ISTA-DASLab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 ↗Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF
ISTA-DASLab**A 512-expert mixture-of-experts model with half of its experts removed**, targeted at code and retaining multimodal capability. **58.4 GB** against 354 GB at BF16, an effective **1.89 bits per parameter of the original transformer**. > **Update, October 17, 2026.** The model has been improved: looping is reduced and coding performance is higher, with SWE-bench Verified rising from 75.60 to 79.20 and LiveCodeBench v6 from 86.28 to 87.43. Only the first shard changed; if you downloaded the earlier build, re-download that shard. This release is a capability-targeted compression of Qwen3.8-Flash-Next. Half of the routed experts are removed from the model rather than quantized, and the remaining weights are stored at 3.5 bpw.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-Flash-Next-GSQ-RCO-GGUF
ISTA-DASLab**Non-uniform GGUF quantizations** of a 512-expert MoE, produced with **GSQ** and **RCO**, with a vision projector for multimodal use. This repository provides GGUF quantizations of **Qwen3.8-Flash-Next** at four sizes, together with the model's vision projector (`mmproj`) for multimodal use. In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF and run unmodified in `llama.cpp`, Ollama, and LM Studio. A code-specialized variant is released separately as Qwen3.8-Flash-Next-GSQ-RCO-Coder, which retains 256 of the 512 routed experts per layer at an effective 1.89 bpw over the original parameters, for a 58.4 GB total.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-Flash-Next-P48NVFP4-MoESQ
ISTA-DASLab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 ↗Qwen3-8B-GGUF-GSQ
ISTA-DASLab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 ↗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 ↗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.