Qwen3 8B

vLLM · BF16 · 16 GB

Qwen3 8B in BF16 on vLLM; fits 24 GB cards; the same template runs on NVIDIA (CUDA) and AMD (ROCm) GPUs.

Chat in your browser, plus an OpenAI-compatible API.

Publishedvllmbf16LLM inference

Needs 22 GiB of GPU memory · Runs on NVIDIA, AMD

Pick a machine

No machine can run this right now.

New machines appear as hosts connect them.

A smaller version runs now:

Qwen3 8B Q4_K_M (llama.cpp, any GPU) from $0.01/h

Have a GPU? Earn with it See all machines

Doesn't fit (4)

1× Apple M5 Max (40-core GPU) · New hostno inference runtime for this machine's backend1× Apple M4 Pro (20-core GPU) · New hostno inference runtime for this machine's backend1× Apple M4 · New hostno inference runtime for this machine's backend1× Apple M1 Pro (14-core GPU) · New hostno inference runtime for this machine's backend

Template details

Rating: No ratings yet
Runs: 0
Min VRAM: 24 GB
Backend: Set by the machine you pick
Weights: 16 GB
Version: vllm-qwen3-8b-v2-v2.0.0
Image digest: 4895d4c39da6…
Health check: SSH probe on the leased endpoint

We match GPUs on their measured runtime and dedicated VRAM. A hardware report doesn't qualify another vendor's backend.

#llm #chat #openai-api #vllm #awq

Reviews

No reviews yet.