Small
bigscience-small-testing specs, VRAM requirements, and which GPUs can run it.
bitnet-b1.58-2B-4T specs, VRAM requirements, and which GPUs can run it.
bitnet-b1.58-2B-4T-bf16 specs, VRAM requirements, and which GPUs can run it.
bloom-1b1 specs, VRAM requirements, and which GPUs can run it.
bloom-1b1-intermediate specs, VRAM requirements, and which GPUs can run it.
bloom-1b7 specs, VRAM requirements, and which GPUs can run it.
bloom-1b7-intermediate specs, VRAM requirements, and which GPUs can run it.
bloom-560m specs, VRAM requirements, and which GPUs can run it.
bloom-560m-intermediate specs, VRAM requirements, and which GPUs can run it.
bloom-7b1-petals specs, VRAM requirements, and which GPUs can run it.
bloomz-1b1 specs, VRAM requirements, and which GPUs can run it.
bloomz-1b7 specs, VRAM requirements, and which GPUs can run it.
bloomz-560m specs, VRAM requirements, and which GPUs can run it.
Bolmo-1B specs, VRAM requirements, and which GPUs can run it.
Bonsai-8B-mlx-1bit specs, VRAM requirements, and which GPUs can run it.
codegemma-2b specs, VRAM requirements, and which GPUs can run it.
convergent-llama-300M-muon-isolate-1 specs, VRAM requirements, and which GPUs can run it.
convergent-llama-300M-muon-window-2 specs, VRAM requirements, and which GPUs can run it.
convergent-llama-300M-muon-window-4 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170m-GR specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GR-1000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GR-16000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GR-31000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GR-46000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GR-61000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GRS-112000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GRS-2000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GRS-26000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GRS-50000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-GRS-76000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170m-UR90 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-UR90-1000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-UR90-46000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-170M-UR90-61000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-3b-GR-HM-1000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-3b-GR-HM-11000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-3b-GR-HM-21000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-3b-GR-HM-31000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-3b-GR-HM-41000 specs, VRAM requirements, and which GPUs can run it.
Dayhoff-3b-GR-HM-c specs, VRAM requirements, and which GPUs can run it.
DeepSeek-R1-0528-Qwen3-8B-MLX-4bit specs, VRAM requirements, and which GPUs can run it.
DeepSeek-R1-0528-Qwen3-8B-MLX-8bit specs, VRAM requirements, and which GPUs can run it.
DeepSeek-R1-Distill-Qwen-1.5B specs, VRAM requirements, and which GPUs can run it.
DialoGPT-small specs, VRAM requirements, and which GPUs can run it.
distilgpt2 specs, VRAM requirements, and which GPUs can run it.
distill-bloom-1b3 specs, VRAM requirements, and which GPUs can run it.
distill-bloom-1b3-10x specs, VRAM requirements, and which GPUs can run it.
ELM specs, VRAM requirements, and which GPUs can run it.
Falcon-E-1B-Base specs, VRAM requirements, and which GPUs can run it.
Falcon-E-1B-Instruct specs, VRAM requirements, and which GPUs can run it.
Falcon-E-3B-Instruct specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-0.5B-Base specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-0.5B-Instruct specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-1.5B-Base specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-1.5B-Deep-Base specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-1.5B-Deep-Instruct specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-1.5B-Instruct specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-Tiny-90M-Base specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-Tiny-90M-Instruct specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-Tiny-90M-Instruct-pre-DPO specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-Tiny-Multilingual-100M-Base specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-Tiny-Multilingual-100M-Instruct specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-Tiny-R-0.6B specs, VRAM requirements, and which GPUs can run it.
Falcon-H1-Tiny-R-90M specs, VRAM requirements, and which GPUs can run it.
falcon-mamba-tiny-dev specs, VRAM requirements, and which GPUs can run it.
Falcon3-1B-Instruct specs, VRAM requirements, and which GPUs can run it.
Falcon3-1B-Instruct-1.58bit specs, VRAM requirements, and which GPUs can run it.
Falcon3-7B-Instruct-1.58bit specs, VRAM requirements, and which GPUs can run it.
Faust-1 specs, VRAM requirements, and which GPUs can run it.
gemma-1.1-2b-it specs, VRAM requirements, and which GPUs can run it.
gemma-2-2b-it specs, VRAM requirements, and which GPUs can run it.
gemma-2-2b-jpn-it specs, VRAM requirements, and which GPUs can run it.
gemma-2b specs, VRAM requirements, and which GPUs can run it.
gemma-3-1b-it specs, VRAM requirements, and which GPUs can run it.
gemma-3-1b-it-qat-int4-unquantized specs, VRAM requirements, and which GPUs can run it.
gemma-3-1b-it-qat-q4_0-unquantized specs, VRAM requirements, and which GPUs can run it.
gemma-3-270m specs, VRAM requirements, and which GPUs can run it.
gemma-3-270m-it-qat-q4_0-unquantized specs, VRAM requirements, and which GPUs can run it.
gemma-3-270m-qat-q4_0-unquantized specs, VRAM requirements, and which GPUs can run it.
gemma-4-e4b-it-OptiQ-4bit specs, VRAM requirements, and which GPUs can run it.
gpt-neo-1.3B specs, VRAM requirements, and which GPUs can run it.
gpt-neo-125m specs, VRAM requirements, and which GPUs can run it.
gpt-neo-2.7B specs, VRAM requirements, and which GPUs can run it.
gpt-oss-120b-Eagle3-long-context specs, VRAM requirements, and which GPUs can run it.
gpt2 specs, VRAM requirements, and which GPUs can run it.
gpt2-large specs, VRAM requirements, and which GPUs can run it.
gpt2-medium specs, VRAM requirements, and which GPUs can run it.
gpt2-mini specs, VRAM requirements, and which GPUs can run it.
h2ovl-mississippi-2b specs, VRAM requirements, and which GPUs can run it.
h2ovl-mississippi-800m specs, VRAM requirements, and which GPUs can run it.
internlm2_5-1_8b-chat specs, VRAM requirements, and which GPUs can run it.
internlm2-chat-1_8b specs, VRAM requirements, and which GPUs can run it.
internlm2-math-plus-1_8b specs, VRAM requirements, and which GPUs can run it.
Jamba-tiny-random specs, VRAM requirements, and which GPUs can run it.
japanese-gpt-neox-small specs, VRAM requirements, and which GPUs can run it.
japanese-stablelm-2-base-1_6b specs, VRAM requirements, and which GPUs can run it.
japanese-stablelm-2-instruct-1_6b specs, VRAM requirements, and which GPUs can run it.
japanese-stablelm-3b-4e1t-instruct specs, VRAM requirements, and which GPUs can run it.
LFM2-1.2B specs, VRAM requirements, and which GPUs can run it.
LFM2.5-1.2B-Instruct specs, VRAM requirements, and which GPUs can run it.
LFM2.5-1.2B-Instruct-MLX-4bit specs, VRAM requirements, and which GPUs can run it.
LFM2.5-1.2B-Instruct-MLX-6bit specs, VRAM requirements, and which GPUs can run it.
LFM2.5-1.2B-Instruct-MLX-8bit specs, VRAM requirements, and which GPUs can run it.
LFM2.5-1.2B-Thinking specs, VRAM requirements, and which GPUs can run it.
Llama-3.2-1B specs, VRAM requirements, and which GPUs can run it.
Llama-3.2-1B-Instruct specs, VRAM requirements, and which GPUs can run it.
Llama-3.2-1B-Instruct-FP8 specs, VRAM requirements, and which GPUs can run it.
Llama-3.2-1B-Instruct-FP8-dynamic specs, VRAM requirements, and which GPUs can run it.
llama-300M-v3-original specs, VRAM requirements, and which GPUs can run it.
llama-300M-v5-isolate specs, VRAM requirements, and which GPUs can run it.
llama-300M-v5-window_2 specs, VRAM requirements, and which GPUs can run it.
llama-300M-v5-window_4 specs, VRAM requirements, and which GPUs can run it.
llama-600M-v4-isolate specs, VRAM requirements, and which GPUs can run it.
Llama-Guard-3-1B specs, VRAM requirements, and which GPUs can run it.
mamba-130m-hf specs, VRAM requirements, and which GPUs can run it.
mini-coder-1.7b specs, VRAM requirements, and which GPUs can run it.
Nemotron-Flash-1B specs, VRAM requirements, and which GPUs can run it.
Nemotron-Flash-3B specs, VRAM requirements, and which GPUs can run it.
nmt_21 specs, VRAM requirements, and which GPUs can run it.
OLMo-1B specs, VRAM requirements, and which GPUs can run it.
OLMo-1B-0724-hf specs, VRAM requirements, and which GPUs can run it.
OLMo-1B-hf specs, VRAM requirements, and which GPUs can run it.
OLMo-2-0425-1B specs, VRAM requirements, and which GPUs can run it.
OLMo-2-0425-1B-early-training specs, VRAM requirements, and which GPUs can run it.
OLMo-2-0425-1B-Instruct specs, VRAM requirements, and which GPUs can run it.
OLMo-2-0425-1B-RLVR1 specs, VRAM requirements, and which GPUs can run it.
OpenReasoning-Nemotron-1.5B specs, VRAM requirements, and which GPUs can run it.
OTel-LLM-1B-IT specs, VRAM requirements, and which GPUs can run it.
OTel-LLM-270M-IT specs, VRAM requirements, and which GPUs can run it.
phi-1 specs, VRAM requirements, and which GPUs can run it.
phi-1_5 specs, VRAM requirements, and which GPUs can run it.
phi-2 specs, VRAM requirements, and which GPUs can run it.
polyglot-ko-1.3b specs, VRAM requirements, and which GPUs can run it.
pythia-1.4b specs, VRAM requirements, and which GPUs can run it.
pythia-1.4b-deduped specs, VRAM requirements, and which GPUs can run it.
pythia-14m specs, VRAM requirements, and which GPUs can run it.
pythia-14m-deduped specs, VRAM requirements, and which GPUs can run it.
pythia-160m-deduped specs, VRAM requirements, and which GPUs can run it.
pythia-160m-deduped-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-160m-seed1 specs, VRAM requirements, and which GPUs can run it.
pythia-160m-seed2 specs, VRAM requirements, and which GPUs can run it.
pythia-160m-seed3 specs, VRAM requirements, and which GPUs can run it.
pythia-160m-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-1b specs, VRAM requirements, and which GPUs can run it.
pythia-1b-deduped-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-1b-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-2.8b-deduped specs, VRAM requirements, and which GPUs can run it.
pythia-2.8b-deduped-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-2.8b-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-31m specs, VRAM requirements, and which GPUs can run it.
pythia-31m-deduped specs, VRAM requirements, and which GPUs can run it.
pythia-410m specs, VRAM requirements, and which GPUs can run it.
pythia-410m-deduped specs, VRAM requirements, and which GPUs can run it.
pythia-410m-deduped-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-410m-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-70m-deduped specs, VRAM requirements, and which GPUs can run it.
pythia-70m-deduped-v0 specs, VRAM requirements, and which GPUs can run it.
pythia-70m-v0 specs, VRAM requirements, and which GPUs can run it.
Qwen2-0.5B-Instruct specs, VRAM requirements, and which GPUs can run it.
Qwen2-1.5B-Instruct specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-0.5B specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-0.5B-Instruct specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-1.5B specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-1.5B-Instruct specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-1.5B-Instruct-AWQ specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-1.5B-quantized.w8a8 specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-Coder-0.5B-Instruct specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-Coder-1.5B-Instruct specs, VRAM requirements, and which GPUs can run it.
Qwen2.5-Math-1.5B specs, VRAM requirements, and which GPUs can run it.
Qwen3-0.6B specs, VRAM requirements, and which GPUs can run it.
Qwen3-0.6B-FP8 specs, VRAM requirements, and which GPUs can run it.
Qwen3-1.7B specs, VRAM requirements, and which GPUs can run it.
Qwen3-1.7B-Base specs, VRAM requirements, and which GPUs can run it.
Qwen3-1.7B-GPTQ-Int8 specs, VRAM requirements, and which GPUs can run it.
Qwen3.5-0.8B-OptiQ-4bit specs, VRAM requirements, and which GPUs can run it.
Qwen3Guard-Gen-0.6B specs, VRAM requirements, and which GPUs can run it.
recurrentgemma-2b specs, VRAM requirements, and which GPUs can run it.
SmolLM-1.7B-Instruct-quantized.w4a16 specs, VRAM requirements, and which GPUs can run it.
SmolLM-135M-Instruct specs, VRAM requirements, and which GPUs can run it.
SmolLM2-135M specs, VRAM requirements, and which GPUs can run it.
SmolLM2-135M-Instruct specs, VRAM requirements, and which GPUs can run it.
stable-code-3b specs, VRAM requirements, and which GPUs can run it.
stablelm-2-1_6b specs, VRAM requirements, and which GPUs can run it.
stablelm-2-1_6b-chat specs, VRAM requirements, and which GPUs can run it.
stablelm-2-zephyr-1_6b specs, VRAM requirements, and which GPUs can run it.
stablelm-3b-4e1t specs, VRAM requirements, and which GPUs can run it.
stablelm-zephyr-3b specs, VRAM requirements, and which GPUs can run it.
stories15M_MOE specs, VRAM requirements, and which GPUs can run it.
test-bloomd-6b3 specs, VRAM requirements, and which GPUs can run it.
tiny-random-Gemma2ForCausalLM specs, VRAM requirements, and which GPUs can run it.
tiny-random-stablelm-2 specs, VRAM requirements, and which GPUs can run it.
TinyLlama-1.1B-Chat-v0.3-GPTQ specs, VRAM requirements, and which GPUs can run it.
TinyLlama-1.1B-Chat-v1.0 specs, VRAM requirements, and which GPUs can run it.
TinySolar-248m-4k specs, VRAM requirements, and which GPUs can run it.
tinyteapot specs, VRAM requirements, and which GPUs can run it.
txgemma-2b-predict specs, VRAM requirements, and which GPUs can run it.
vaultgemma-1b specs, VRAM requirements, and which GPUs can run it.