What fits in a RTX 5070's 12 GB?
Blackwell. 12 GB VRAM, verified from the vendor datasheet. On-demand rate from $0.247/hr, sourced from 1 provider.
12 GB
VRAM
Blackwell
Architecture
$0.247/hr
From
1
Providers
Last updated: 2026-10-07 11:14:43 UTCRefreshes hourly
Models that fit at FP16 (12 GB)
- google-bert/bert-base-uncased (110M)
- Qwen/Qwen3-0.6B (752M)
- openai-community/gpt2 (137M)
- Qwen/Qwen2.5-1.5B-Instruct (1.5B)
- Qwen/Qwen2.5-3B-Instruct (3.1B)
- Qwen/Qwen3.5-4B (4.7B)
- openai/whisper-large-v3-turbo (809M)
- Qwen/Qwen3-Embedding-0.6B (596M)
- meta-llama/Llama-3.2-1B-Instruct (1.2B)
- Qwen/Qwen3-4B (4.0B)
- Qwen/Qwen2.5-0.5B-Instruct (494M)
- openai/whisper-large-v3 (1.5B)
- Qwen/Qwen3-ASR-1.7B (2.3B)
- Qwen/Qwen3-VL-4B-Instruct (4.4B)
- Qwen/Qwen2.5-VL-3B-Instruct (3.8B)
- Qwen/Qwen3-1.7B (2.0B)
- EleutherAI/pythia-160m (213M)
- Qwen/Qwen3-4B-Instruct-2507 (4.0B)
- google/gemma-4-E2B-it (5.1B)
- Qwen/Qwen3-Embedding-4B (4.0B)
- google/gemma-3-1b-it (1000M)
- baidu/Unlimited-OCR (3.3B)
- RadixArk/Kimi-K3-DSpark (2.2B)
- openai/whisper-small (242M)
- datalab-to/chandra-ocr-2 (5.3B)
- Qwen/Qwen3-VL-2B-Instruct (2.1B)
- Qwen/Qwen3.5-2B (2.3B)
- microsoft/Florence-2-base (232M)
- HuggingFaceTB/SmolLM2-135M (135M)
- MahmoudAshraf/mms-300m-1130-forced-aligner (315M)
- deepseek-ai/DeepSeek-OCR (3.3B)
- Qwen/Qwen3.5-0.8B (873M)
- Qwen/Qwen3-Reranker-4B (4.0B)
- facebook/sam3 (860M)
- mistralai/Voxtral-Mini-4B-Realtime-2602 (4.4B)
- zai-org/GLM-OCR (1.3B)
- Qwen/Qwen3-VL-Reranker-2B (2.1B)
- mlx-community/parakeet-tdt-0.6b-v2 (618M)
- prism-ml/Bonsai-27B-mlx-1bit (1.7B)
- Qwen/Qwen3-1.7B-Base (1.7B)
Models that fit at INT4 (quantized, 12 GB)
- google-bert/bert-base-uncased (110M)
- Qwen/Qwen3-0.6B (752M)
- openai-community/gpt2 (137M)
- Qwen/Qwen3-8B (8.2B)
- Qwen/Qwen3.5-9B (9.7B)
- Qwen/Qwen2.5-7B-Instruct (7.6B)
- Qwen/Qwen3-VL-8B-Instruct (8.8B)
- Qwen/Qwen2.5-VL-7B-Instruct (8.3B)
- Qwen/Qwen2.5-1.5B-Instruct (1.5B)
- Qwen/Qwen2.5-3B-Instruct (3.1B)
- Qwen/Qwen3.5-4B (4.7B)
- openai/whisper-large-v3-turbo (809M)
- Qwen/Qwen3-Embedding-0.6B (596M)
- meta-llama/Llama-3.2-1B-Instruct (1.2B)
- Qwen/Qwen3-4B (4.0B)
- Qwen/Qwen2.5-0.5B-Instruct (494M)
- meta-llama/Llama-3.1-8B-Instruct (8.0B)
- openai/whisper-large-v3 (1.5B)
- google/gemma-4-E4B-it (8.0B)
- Qwen/Qwen3-ASR-1.7B (2.3B)
- Qwen/Qwen3-VL-4B-Instruct (4.4B)
- Qwen/Qwen2.5-VL-3B-Instruct (3.8B)
- Qwen/Qwen3-1.7B (2.0B)
- EleutherAI/pythia-160m (213M)
- Qwen/Qwen3-4B-Instruct-2507 (4.0B)
- google/gemma-4-E2B-it (5.1B)
- google/gemma-4-12B-it (12.0B)
- Qwen/Qwen3-Embedding-4B (4.0B)
- unsloth/Qwen3.6-27B-NVFP4 (21.2B)
- google/gemma-3-1b-it (1000M)
- baidu/Unlimited-OCR (3.3B)
- RadixArk/Kimi-K3-DSpark (2.2B)
- openai/whisper-small (242M)
- datalab-to/chandra-ocr-2 (5.3B)
- Qwen/Qwen3-VL-2B-Instruct (2.1B)
- Qwen/Qwen3.5-2B (2.3B)
- microsoft/Florence-2-base (232M)
- Qwen/Qwen2.5-14B-Instruct (14.8B)
- unsloth/Qwen3.8-27B-NVFP4 (19.9B)
- HuggingFaceTB/SmolLM2-135M (135M)
Caveat: Requires a quantized checkpoint actually published for the model, check its Hugging Face page before relying on this.
Live pricing
$0.247/hr on-demand rate, 4 live offers across 1 provider and 1 region, refreshed hourly.
