Loading…
Loading…
Models / Qwen3.8 / Qwen3.8 27B
Vision + text · served with vLLM · ↓ 374.4K downloads a month · View on Hugging Face
nicosuter/Qwen3.8-27B-AWQ needs about 28.5 GB of GPU memory for conversations of up to 8,192 tokens. It runs on 2x RTX 5060 Ti from $0.23/h right now.
The same model packaged differently: a quantized version needs less GPU memory and runs on a cheaper machine.
| Version | Runtime | Weights | GPU memory | Cheapest machine now | Deploy |
|---|---|---|---|---|---|
| OriginalQwen/Qwen3.8-27B | vLLM | 56 GB | 66.3 GB | $0.38/h Nvidia GB10 | Deploy |
| FP8Qwen/Qwen3.8-27B-FP8 | vLLM | 31 GB | 38.9 GB | $0.34/h 4x RTX 3060 | Deploy |
| AWQ INT4 (cyankiwi)cyankiwi/Qwen3.8-27B-AWQ-INT4 | vLLM | 21 GB | 28 GB | $0.22/h 2x RTX 5060 Ti | Deploy |
| NVFP4 (RadixArk)RadixArk/Qwen3.8-27B-NVFP4 | vLLM | 22 GB | 29 GB | $0.22/h 2x RTX 5060 Ti | Deploy |
| AWQ (nicosuter)nicosuter/Qwen3.8-27B-AWQ | vLLM | 22 GB | 28.5 GB | $0.22/h |
$0.23/h from your balance while it runs, billed by the hour; stop it from its page. GridPup rents the machine, which downloads the model from Hugging Face (usually ready in 10 to 15 minutes), and gives you an https address, keys and a Playground.
| NVFP4 RTX5090 (gittensor-model-hub)gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090 | vLLM | 18 GB | 24.5 GB | $0.22/h 2x RTX A4000 | Deploy |
| NVFP4 (nvidia)nvidia/Qwen3.8-27B-NVFP4 | vLLM | 22 GB | 29 GB | $0.22/h 2x RTX 5060 Ti | Deploy |
| MTP NVFP4 (sakamakismile)sakamakismile/Qwen3.8-27B-MTP-NVFP4 | vLLM | 21 GB | 27.5 GB | $0.22/h 2x RTX A4000 | Deploy |
| INT4 (RedHatAI)RedHatAI/Qwen3.8-27B-INT4 | vLLM | 19 GB | 26.2 GB | $0.22/h 2x RTX A4000 | Deploy |
| W4A16 AWQ (philbert440)philbert440/Qwen3.8-27B-W4A16-AWQ | vLLM | 20 GB | 26.3 GB | $0.22/h 2x RTX A4000 | Deploy |
| NVFP4 (PassingByPixels)PassingByPixels/Qwen3.8-27B-NVFP4 | vLLM | 21 GB | 27.5 GB | $0.22/h 2x RTX A4000 | Deploy |
| QUASAR NVFP4 (QUASAR-QAT)QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 | vLLM | 21 GB | 27.5 GB | $0.22/h 2x RTX A4000 | Deploy |
| NVFP4 (Inferact)Inferact/Qwen3.8-27B-NVFP4 | vLLM | 26 GB | 33.9 GB | $0.32/h 2x RTX 3080 | Deploy |
| GPTQ Int4 sym G128 MTP BF16 (SergiioB)SergiioB/Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16 | vLLM | 20 GB | 26.3 GB | $0.22/h 2x RTX A4000 | Deploy |
| AWQ W4A16 ASYM (Ar4ikov)Ar4ikov/Qwen3.8-27B-AWQ-W4A16-ASYM | vLLM | 20 GB | 26.3 GB | $0.22/h 2x RTX A4000 | Deploy |
| GPTQ Int4 (sokada4)sokada4/Qwen3.8-27B-GPTQ-Int4 | vLLM | 20 GB | 26.3 GB | $0.22/h 2x RTX A4000 | Deploy |
| GPTQ W4A16 (pearsonkyle)pearsonkyle/Qwen3.8-27B-GPTQ-W4A16 | vLLM | 19 GB | 26.2 GB | $0.22/h 2x RTX A4000 | Deploy |
| Uncensored FP8 (orcarouter)orcarouter/Qwen3.8-27B-Uncensored-FP8Licence to accept | vLLM | 31 GB | ~39.3 GB | $0.34/h 4x RTX 3060 |
| NVFP4 BF16 LMHead (RadixArk)RadixArk/Qwen3.8-27B-NVFP4-BF16-LMHead | vLLM | 24 GB | 31 GB | $0.32/h 2x RTX 3080 | Deploy |
| NVFP4 DGX SPARK (autotrust)autotrust/Qwen3.8-27B-NVFP4-DGX-SPARK | vLLM | 22 GB | 29 GB | $0.22/h 2x RTX 5060 Ti | Deploy |
| Uncensored NVFP4 (orcarouter)orcarouter/Qwen3.8-27B-Uncensored-NVFP4Licence to accept | vLLM | 25 GB | ~31.8 GB | $0.32/h 2x RTX 3080 |
| GPTQ Int4 sym G128 MTP BF16 (mikeinnyc)mikeinnyc/Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16 | vLLM | 20 GB | 26.3 GB | $0.22/h 2x RTX A4000 | Deploy |
| MXFP8 MXFP8MTP CT AutoRound (intel-ai)intel-ai/Qwen3.8-27B-MXFP8-MXFP8MTP-CT-AutoRound | vLLM | 32 GB | 39.8 GB | $0.34/h 4x RTX 3060 | Deploy |
| MedErtas v0.1 27B LS (ErtasAI)ErtasAI/MedErtas-v0.1-27B-LS | vLLM | 22 GB | 29 GB | $0.22/h 2x RTX 5060 Ti | Deploy |
| Ternary Bonsai 2 27B vllm (fraserprice)fraserprice/Ternary-Bonsai-2-27B-vllm | vLLM | 10 GB | 16 GB | $0.15/h 2x RTX 3060 | Deploy |
| MiniMax H3 Image PE (MiniMaxAI)MiniMaxAI/MiniMax-H3-Image-PE | vLLM | 18 GB | 24.5 GB | $0.22/h 2x RTX A4000 | Deploy |
| OrcaSAQ 2 27B (orcarouter)orcarouter/OrcaSAQ-2-27B | vLLM | 12 GB | 18.2 GB | $0.15/h 2x RTX 3060 | Deploy |
| Escha W2 (EschaLabs)EschaLabs/Qwen3.8-27B-Escha-W2 | vLLM | 10 GB | 15.9 GB | $0.11/h RTX 4060 Ti | Deploy |
| NVFP4 ONNX (tlwu)tlwu/Qwen3.8-27B-NVFP4-ONNX | ONNX Runtime GenAI | 23 GB | 29.7 GB | $0.09/h Nvidia V100 |
Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability of 90% or more that download at 200 Mbit/s or more are offered: the machine fetches the model itself.