Together AI

DeepSeek R1 Distill Llama 70B

Deepseek OCR 2

Cogito V1 Preview Qwen 32B

Cogito V1 Preview Qwen 14B

Cogito V1 Preview Llama 8B

Nemotron 3 Nano Omni 30B A3b Reasoning Fp8

Cogito V1 Preview Llama 70B Turbo

Cogito V1 Preview Llama 70B

nim/nvidia/llama-3.1-nemotron-70b-instruct

nim/nv-mistralai/mistral-nemo-12b-instruct

nim/meta/llama-3.1-8b-instruct

nim/meta/llama-3.1-70b-instruct

Gemma 2 9B It

Llama 4 Scout 17B 16E Instruct Fp8 Lora

Qwen3 Next 80B A3b Thinking

Qwen2.5 32B

Nous Hermes 2 Mixtral 8X7B Dpo

Qwen3-VL-32B-Instruct

GLM 4.7 Fp8

Meta Llama 3.1 70B Instruct Turbo

Qwen3 Coder 30B A3b Instruct

Qwen 2 (1.5B)

Qwen3 4B Base

Gemma 4 26B A4b It

Facebook CWM

Holo3 35B A3b

Mistral Small (24B) Instruct 25.01

Gemma 4 E4B-it

Qwen3-VL-8B-Instruct

Qwen3.6 Plus

Cogito v2.1 671B

EssentialAI Rnj-1 Instruct

LFM2-24B-A2B

Arize AI Qwen 2 1.5B Instruct

Gemma 3N E4B Instruct

Meta Llama 3 8B Instruct Lite

Meta Llama 3.3 70B Instruct Turbo

Qwen2.5 7B Instruct Turbo

Qwen3 235B A22B Instruct 2507 FP8 Throughput

Qwen3 Coder 480B A35B Instruct Fp8

Qwen3.5 9B FP8

GLM 5 Fp4

OpenAI GPT-OSS 20B

OpenAI GPT-OSS 120B

Qwen3.5 397B A17b

Gemma 4 31B-it FP8

Pearl-ai Gemma-4-31B-it-pearl

MiniMax M2.7 FP4

Kimi K2.6 Fp4

GLM 5.1 FP4

Deepseek V4 Pro