azureFoundry/azureml-fireworks/FW-NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16@1
NVIDIA Nemotron 3 Ultra 550B A55B BF16 is a 550B-parameter hybrid Mamba-2 and LatentMoE language model with 55B active parameters, configurable reasoning, tool use, and multilingual support for complex agentic workloads.
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-GPT-OSS-120B@1
gpt-oss-120b is an open-weight Mixture-of-Experts model from OpenAI with 117B total parameters, designed for powerful reasoning, agentic tasks, and production-grade general-purpose use cases.
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-GPT-OSS-20B@1
OpenAI gpt-oss-20b is an open-weight Mixture-of-Experts model with 21B total parameters and 3.6B active parameters, designed for lower-latency reasoning, agentic tasks, and local or specialized use cases.
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-PaddleOCR-VL-1.6@1
PaddleOCR VL 1.6 is a compact 0.9B vision-language model for document parsing, including OCR, tables, formulas, charts, and seals, with image input and a 131K-token context window.
- Context window
- 131,072
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, visionInput
azureFoundry/azureml-fireworks/FW-Qwen3-14B@1
Qwen3 14B is a 14.8B-parameter dense causal language model from Alibaba featuring seamless switching between thinking and non-thinking modes, strong reasoning, coding, and agent capabilities, support for 100+ languages, and a 131K token context window with
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-Qwen3-32B@1
Qwen3 32B is a 32.8B-parameter dense causal language model from Alibaba with thinking and non-thinking modes, strong reasoning, coding, agent capabilities, 100+ language support, and a 131K token context window with YaRN.
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-Qwen3.5-122B-A10B@1
Qwen3.5 122B A10B is a 122B-parameter Mixture-of-Experts vision-language model from Alibaba with 10B activated parameters, featuring Gated Delta Networks, 201 language support, and 262K native context.
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-Qwen3.5-122B-A10B@2
Qwen3.5 122B A10B is a 122B-parameter Mixture-of-Experts vision-language model from Alibaba with 10B activated parameters, featuring Gated Delta Networks, 201 language support, and 262K native context.
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, toolCalling, visionInput
azureFoundry/azureml-fireworks/FW-Qwen3.5-27B@1
Qwen3.5 27B is a 27B-parameter causal language model with a vision encoder, hybrid Gated DeltaNet and Gated Attention architecture, thinking mode by default, 201 language support, and a native 262K token context window.
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, toolCalling, visionInput
azureFoundry/azureml-fireworks/FW-Qwen3.5-35B-A3B@1
Qwen3.5 35B A3B is a 35B-parameter, 3B-activated causal language model that uses a hybrid Gated DeltaNet and sparse Mixture-of-Experts architecture for reasoning, coding, and agent tasks across 201 languages and dialects.
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- toolCalling
azureFoundry/azureml-fireworks/FW-Qwen3.5-397B-A17B@1
Qwen3.5 397B A17B is a 397B-parameter Mixture-of-Experts language model from Alibaba with 17B activated parameters, featuring Gated Delta Networks, 201 language support, and 262K native context. This is the text-only variant of the model.
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-Qwen3.5-397B-A17B@2
Qwen3.5 397B A17B is a 397B-parameter Mixture-of-Experts vision-language model from Alibaba with 17B activated parameters, featuring Gated Delta Networks, 201 language support, 262K native context, and image input support on Fireworks.
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, toolCalling, visionInput
azureFoundry/azureml-fireworks/FW-Qwen3.5-4B@1
Qwen3.5 4B is a 4B-parameter causal language model with a vision encoder, hybrid Gated DeltaNet and Gated Attention architecture, thinking mode by default, 201 language support, and a native 262K token context window.
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, toolCalling, visionInput
azureFoundry/azureml-fireworks/FW-Qwen3.5-9B@1
Qwen3.5 9B is a 9B-parameter causal language model with hybrid Gated DeltaNet/Gated Attention architecture, built for reasoning, coding, and agent workflows with a native 262,144-token context window.
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- toolCalling
azureFoundry/azureml-fireworks/FW-Qwen3.6-27B@1
Qwen3.6 27B is a 27B-parameter dense causal language model from the Qwen3.6 family, offering strong reasoning, coding, and agentic capabilities with seamless thinking/non-thinking modes, multilingual support, and a 262,144-token context window.
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, toolCalling, visionInput
azureFoundry/azureml-fireworks/FW-Qwen3.6-35B-A3B@1
Qwen3.6 35B A3B is a 35B-parameter, 3B-activated causal language model that uses a hybrid Gated DeltaNet and sparse Mixture-of-Experts architecture for reasoning, coding, and agent tasks across 201 languages and dialects.
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-Qwen3.8-27B@1
Qwen3.8 27B is a dense vision-language model from Qwen, listed by Fireworks with 27.3B parameters, hybrid linear/full attention at a 4:1 interval, a 262K-token context window, image input, and function calling support.
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, toolCalling, visionInput