Explore our credit programs for startups and researchers.
LLM Models on Runpod
Deploy and run popular LLM models with your own custom API endpoint. Choose a model below to get started.
openai-community/gpt2
meta-llama/llama-3.1-8b-instruct
meta-llama/meta-llama-3-8b
distilbert/distilgpt2
qwen/qwen2.5-3b-instruct
meta-llama/llama-3.2-1b-instruct
qwen/qwen2.5-7b-instruct
qwen/qwen2.5-1.5b-instruct
qwen/qwen2.5-0.5b
mistralai/mistral-7b-instruct-v0.2
tinyllama/tinyllama-1.1b-chat-v1.0
deepseek-ai/deepseek-r1-distill-llama-8b
qwen/qwen2.5-0.5b-instruct
deepseek-ai/deepseek-r1-distill-qwen-1.5b
orenguteng/llama-3-8b-lexi-uncensored
qwen/qwen2.5-7b-instruct-1m
meta-llama/meta-llama-3-8b-instruct
sarvamai/sarvam-m
huggingfacetb/smollm2-135m
microsoft/phi-2
microsoft/phi-3-mini-4k-instruct
microsoft/phi-4
qwen/qwen2.5-7b
meta-llama/llama-2-7b-hf
qwen/qwen2.5-14b-instruct
huggingfaceh4/zephyr-7b-beta
deepseek-ai/deepseek-r1-distill-qwen-7b
ibm-granite/granite-3.1-8b-instruct
deepseek-ai/deepseek-r1-distill-qwen-14b
meta-llama/llama-guard-3-8b
mistralai/mistral-7b-v0.1
microsoft/phi-3.5-mini-instruct
meta-llama/llama-3.2-3b
huggingfacetb/smollm2-135m-instruct
teknium/openhermes-2.5-mistral-7b
qwen/qwen2.5-3b
mistralai/mistral-7b-instruct-v0.1
nvidia/llama-3.1-nemotron-nano-8b-v1
tiiuae/falcon-7b-instruct
microsoft/dialogpt-medium
mistralai/mistral-7b-v0.3
unsloth/meta-llama-3.1-8b-instruct
lgai-exaone/exaone-deep-7.8b
qwen/qwen2.5-14b
salesforce/llama-xlam-2-8b-fc-r
mistralai/mistral-small-24b-instruct-2501
qwen/qwen2.5-math-1.5b
deepseek-ai/deepseek-llm-7b-chat
lgai-exaone/exaone-deep-2.4b
sao10k/l3-8b-stheno-v3.2
ibm-granite/granite-3.3-2b-instruct
agentica-org/deepscaler-1.5b-preview
lgai-exaone/exaone-3.5-2.4b-instruct
deepseek-ai/deepseek-coder-6.7b-instruct
qwen/qwen2.5-math-7b
ibm-granite/granite-3.3-8b-instruct
mlp-ktlim/llama-3-korean-bllossom-8b
huggingfacetb/smollm2-360m-instruct
huggingfacetb/smollm2-1.7b-instruct
nousresearch/hermes-3-llama-3.1-8b
defog/sqlcoder-7b-2
nvidia/acereason-nemotron-14b
deepseek-ai/deepseek-llm-7b-base
nousresearch/hermes-3-llama-3.2-3b
nvidia/acereason-nemotron-7b
kyutai/helium-1-2b
powerinfer/smallthinker-3b-preview
ibm-granite/granite-3.2-8b-instruct
uer/gpt2-chinese-cluecorpussmall
ibm-granite/granite-3.3-8b-base
fdtn-ai/foundation-sec-8b
bllossom/llama-3.2-korean-bllossom-3b
probemedicalyonseimailab/medllama3-v20
numind/nuextract-1.5
lgai-exaone/exaone-deep-32b
fractalairesearch/fathom-r1-14b
latitudegames/wayfarer-12b
nvidia/acemath-rl-nemotron-7b
nvidia/llama-3.1-nemotron-nano-4b-v1.1
nousresearch/deephermes-3-llama-3-8b-preview
qwen/qwq-32b-awq
nousresearch/nous-hermes-2-mistral-7b-dpo
livekit/turn-detector
contactdoctor/bio-medical-llama-3-8b
ibm-granite/granite-3.2-2b-instruct
valdemardi/deepseek-r1-distill-qwen-32b-awq
mixedbread-ai/mxbai-rerank-base-v2
facebook/kernelllm
mistralai/mistral-small-24b-base-2501
microsoft/phi-4-reasoning-plus
allam-ai/allam-7b-instruct-preview
jinaai/readerlm-v2
naver-hyperclovax/hyperclovax-seed-text-instruct-0.5b
open-thoughts/openthinker3-7b
bytedance-seed/seed-coder-8b-instruct
agentica-org/deepcoder-14b-preview
m-a-p/yue-s1-7b-anneal-en-cot
sakanaai/tinyswallow-1.5b
mixedbread-ai/mxbai-rerank-large-v2
homebrewltd/alphamaze-v0.2-1.5b