Catalog

Models

SortCapability Fastest Cheapest Most benchmarked Largest Newest

$/1M = blended 3:1 in:out price · tok/s = median output speed · via Artificial Analysis · methodology

Showing 2,001–2,100 of 2,482 models

Model	Cap	$/1M	tok/s	Evals	Released
DeepSeek-V3.2 deepseek-ai	—	—	—	—	Dec 1, 2025
Qwen2-1.5B-Instruct Qwen	—	—	—	—	Jun 3, 2024
Meta-Llama-3.1-8B-Instruct-GGUF lmstudio-community	—	—	—	—	Jul 23, 2024
Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS AEON-7	—	—	—	—	Apr 28, 2026
Qwen3-32B-GGUF MaziyarPanahi	—	—	—	—	Apr 28, 2025
gpt-oss-120b-GGUF unsloth	—	—	—	—	Aug 5, 2025
NVIDIA-Nemotron-Nano-9B-v2-Japanese nvidia	—	—	—	—	Feb 4, 2026
llama-68m JackFram	—	—	—	—	Jul 19, 2023
Qwen1.5-MoE-A2.7B Qwen	—	—	—	—	Feb 29, 2024
DeepSeek-R1-Distill-Qwen-32B-abliterated huihui-ai	—	—	—	—	Jan 22, 2025
Qwen2.5-32B-Instruct-GPTQ-Int8 Qwen	—	—	—	—	Sep 17, 2024
Qwen3-30B-A3B-4bit mlx-community	—	—	—	—	Apr 28, 2025
DeepSeek-R1-Distill-Qwen-1.5B-GGUF unsloth	—	—	—	—	Jan 20, 2025
MiniCPM-2B-sft-bf16 openbmb	—	—	—	—	Jan 29, 2024
GPT-4o Realtime (Dec '24) OpenAI	—	—	—	—	Dec 17, 2024
o1-pro OpenAI	—	$263	—	—	Mar 19, 2025
DeepSeek-V2-Chat DeepSeek	—	—	—	—	May 6, 2024
DeepSeek-V2.5 DeepSeek	—	—	—	—	Sep 6, 2024
Apertus-8B-Instruct-2509 swiss-ai	—	—	—	—	Aug 13, 2025
SmolLM2-135M-Instruct HuggingFaceTB	—	—	—	—	Oct 31, 2024
TinyLlama-1.1B-Chat-v1.0 TinyLlama	—	—	—	—	Dec 30, 2023
Moonlight-16B-A3B-Instruct moonshotai	—	—	—	—	Feb 22, 2025
salamandra-7b-instruct BSC-LT	—	—	—	—	Sep 30, 2024
OLMo-2-0425-1B allenai	—	—	—	—	Apr 17, 2025
Qwen3-8B-FP8 Qwen	—	—	—	—	Apr 28, 2025
Qwen2.5-3B-Instruct-AWQ Qwen	—	—	—	—	Sep 17, 2024
LFM2.5-1.2B-Instruct LiquidAI	—	—	—	—	Jan 6, 2026
RnJ-1-Instruct-FP8 Doradus-AI	—	—	—	—	Dec 7, 2025
Grok 3 Reasoning Beta xAI	—	—	—	—	Feb 19, 2025
Llama-3.1-8B-Instruct-FP8 nvidia	—	—	—	—	Aug 29, 2024
LongCat-Flash-Chat meituan-longcat	—	—	—	—	Aug 29, 2025
OTel-LLM-1B-IT farbodtavakkoli	—	—	—	—	Feb 11, 2026
tiny-BloomForCausalLM trl-internal-testing	—	—	—	—	Nov 25, 2024
h2ovl-mississippi-800m h2oai	—	—	—	—	Oct 16, 2024
Qwen3.6-27B-Text-NVFP4-MTP sakamakismile	—	—	—	—	Apr 25, 2026
Llama-3.2-1B-Instruct-FP8-dynamic RedHatAI	—	—	—	—	Sep 25, 2024
OpenELM-1_1B-Instruct apple	—	—	—	—	Apr 12, 2024
Qwen2.5-72B-Instruct-AWQ Qwen	—	—	—	—	Sep 17, 2024
tiny-random-Llama-3 llamafactory	—	—	—	—	Jun 7, 2024
pythia-160m-deduped EleutherAI	—	—	—	—	Feb 8, 2023
MiniMax-M2 MiniMaxAI	—	—	—	—	Oct 22, 2025
LFM2.5-1.2B-Instruct-MLX-8bit lmstudio-community	—	—	—	—	Jan 7, 2026
OLMoE-1B-7B-0924 allenai	—	—	—	—	Jul 20, 2024
TinyLlama-1.1B-Chat-v0.3-AWQ TheBloke	—	—	—	—	Oct 3, 2023
ctrl Salesforce	—	—	—	—	Mar 2, 2022
Qwen3-235B-A22B-FP8 Qwen	—	—	—	—	Apr 28, 2025
Qwen2.5-Math-7B Qwen	—	—	—	—	Sep 16, 2024
HyperCLOVAX-SEED-Think-32B naver-hyperclovax	—	—	—	—	Dec 23, 2025
TinyLlama-1.1B-Chat-v1.0-GPTQ TheBloke	—	—	—	—	Dec 31, 2023
falcon-7b-instruct tiiuae	—	—	—	—	Apr 25, 2023
LLaMA-1B-dj-refine-150B datajuicer	—	—	—	—	Oct 30, 2023
DeepSeek-V3-0324 deepseek-ai	—	—	—	—	Mar 24, 2025
DeepSeek-R1-Distill-Qwen-7B deepseek-ai	—	—	—	—	Jan 20, 2025
tiny-GptOssForCausalLM trl-internal-testing	—	—	—	—	Aug 5, 2025
Gemma-4-31B-IT-NVFP4 nvidia	—	—	—	—	Apr 2, 2026
Qwen3-8B Qwen	—	—	—	—	Apr 27, 2025
Qwen3.5-397B-A17B-NVFP4 nvidia	—	—	—	—	Feb 16, 2026
NVIDIA-Nemotron-Nano-9B-v2-FP8 nvidia	—	—	—	—	Sep 22, 2025
Meta-Llama-3.1-405B-Instruct-GGUF MaziyarPanahi	—	—	—	—	Jul 24, 2024
Llama-3.2-3B meta-llama	—	—	—	—	Sep 18, 2024
h2ovl-mississippi-2b h2oai	—	—	—	—	Oct 15, 2024
Qwen2.5-7B Qwen	—	—	—	—	Sep 15, 2024
bart-large-emojilm KomeijiForce	—	—	—	—	Nov 6, 2023
Qwen2.5-1.5B-Instruct-AWQ Qwen	—	—	—	—	Sep 17, 2024
DeepSeek-V4-Flash deepseek-ai	—	—	—	—	Apr 22, 2026
Qwen3-4B-Base Qwen	—	—	—	—	Apr 28, 2025
gpt2-medium openai-community	—	—	—	—	Mar 2, 2022
Qwen2.5-3B-Instruct-GGUF Qwen	—	—	—	—	Sep 17, 2024
starcoder2-3b bigcode	—	—	—	—	Nov 29, 2023
BioMistral-7B BioMistral	—	—	—	—	Feb 14, 2024
Qwen3-30B-A3B-FP8-dynamic RedHatAI	—	—	—	—	May 3, 2025
Qwen3-30B-A3B-Thinking-2507 Qwen	—	—	—	—	Jul 29, 2025
llama-160m JackFram	—	—	—	—	May 26, 2023
tiny-DeepseekV3ForCausalLM-0528 trl-internal-testing	—	—	—	—	Jun 4, 2025
Qwen3-0.6B-unsloth-bnb-4bit unsloth	—	—	—	—	Apr 28, 2025
LFM2-1.2B LiquidAI	—	—	—	—	Jul 10, 2025
granite-4.0-tiny-preview ibm-granite	—	—	—	—	Apr 30, 2025
Meta-Llama-3-8B NousResearch	—	—	—	—	Apr 18, 2024
Qwen1.5-7B Qwen	—	—	—	—	Jan 22, 2024
Qwen2-1.5B Qwen	—	—	—	—	May 31, 2024
Qwen3-30B-A3B-Thinking-2507-AWQ-4bit cyankiwi	—	—	—	—	Jul 30, 2025
japanese-gpt-neox-small rinna	—	—	—	—	Aug 31, 2022
phi-4-GGUF MaziyarPanahi	—	—	—	—	Jan 8, 2025
Qwen3-1.7B-Base Qwen	—	—	—	—	Apr 28, 2025
MiniMax-M2.5 MiniMaxAI	—	—	—	—	Feb 12, 2026
Qwen3-30B-A3B-GGUF MaziyarPanahi	—	—	—	—	Apr 29, 2025
DialoGPT-medium microsoft	—	—	—	—	Mar 2, 2022
Qwen3-235B-A22B-Instruct-2507 Qwen	—	—	—	—	Jul 21, 2025
MiniMax-M2.5-NVFP4 nvidia	—	—	—	—	Mar 11, 2026
Qwen2.5-Coder-7B-Instruct-bnb-4bit unsloth	—	—	—	—	Sep 23, 2024
GLM-5.1-FP8 zai-org	—	—	—	—	Apr 3, 2026
gpt-neo-125m EleutherAI	—	—	—	—	Mar 2, 2022
Olmo-3-7B-Think allenai	—	—	—	—	Nov 18, 2025
Meta-Llama-3-8B-Instruct NousResearch	—	—	—	—	Apr 18, 2024
LFM2.5-350M LiquidAI	—	—	—	—	Mar 31, 2026
Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP sakamakismile	—	—	—	—	Apr 25, 2026
GLM-4.7-Flash-MLX-6bit lmstudio-community	—	—	—	—	Jan 19, 2026
reformer-crime-and-punishment google	—	—	—	—	Mar 2, 2022
tiny-Qwen3ForCausalLM-Instruct-2507 trl-internal-testing	—	—	—	—	Apr 17, 2026
Meta-Llama-3.1-8B-Instruct-bnb-4bit unsloth	—	—	—	—	Jul 23, 2024

← PrevPage 21 of 25Next →