Browse currently supported Hugging Face and official ComfyUI models, compare the hardware profile, and review a live GPU offer before spending credits.
21 launchable models matching “nm-testing” on this page. Exact, runtime-qualified revisions only.
SmolLM-1.7B-Instruct-quantized.w4a16 is a validated text generation model.
Meta-Llama-3-8B-Instruct-nonuniform-test is a validated text generation model.
tinyllama-oneshot-w4a16-channel-v2 is a validated text generation model.
tinyllama-oneshot-w8w8-test-static-shape-change is a validated text generation model.
tinyllama-oneshot-w4a16-group128-v2 is a validated text generation model.
Meta-Llama-3-8B-FP8-compressed-tensors-test is a validated text generation model.
tinyllama-oneshot-w8a8-channel-dynamic-token-v2 is a validated text generation model.
tinyllama-oneshot-w8a8-dynamic-token-v2 is a validated text generation model.
tinyllama-oneshot-w8-channel-a8-tensor is a validated text generation model.
tinyllama-oneshot-w8a16-per-channel is a validated text generation model.
Qwen3-30B-A3B-FP8-block is a validated text generation model.
Qwen2-1.5B-Instruct-FP8W8 is a validated text generation model.
Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform is a validated text generation model.
convert_awq_w4a16_asym-e2e is a validated text generation model.
TinyLlama-1.1B-compressed-tensors-kv-cache-scheme is a validated text generation model.
DeepSeek-R1-Distill-Qwen-32B-NVFP4 is a validated text generation model.
llama7b-one-shot-2_4-w4a16-marlin24-t is a validated text generation model.
tinyllama-oneshot-w8a8-dynamic-token-v2-asym is a validated text generation model.
tinyllama-oneshot-w8a8-static-v2 is a validated text generation model.
Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test is a validated text generation model.
llama3-8b-w8_channel-a8_tensor-compressed is a validated text generation model.
