Model Library/Qwen3 Coder 30B

Qwen

Qwen3 Coder 30B

A coding model for agents and editors, with tool calls turned on.

CodingTextvLLMllama.cpp5 buildsOne-click preset

Recommended: RTX 5090, 32 GB GDDR7, $0.69 / hour, billed per minute. Check availability.

Configure

Every build below is published on Hugging Face and fits at least one GPU we rent. Pick the quantization and engine: the memory it needs, the GPUs it fits and the recommended GPU follow, and Deploy takes that exact build, revision and GPU to the console. Only the one-click preset is tested by GPUwerk.

Qwen3 Coder 30B, AWQ 4-bit on vLLM
QuantizationAWQ 4-bit
EnginevLLM
StatusOne-click preset
Weights16.8 GB
GPU memory it needsAbout 22 GB as the preset serves it
Recommended GPURTX 5090, $0.69 / hour
Weights sourceQuantTrio/Qwen3-Coder-30B-A3B-Instruct-AWQ, revision c58857a7f41c
Licence on the cardapache-2.0
GPUs Qwen3 Coder 30B AWQ 4-bit does and does not fit
GPUMemoryPriceAvailabilityDeploy
RTX 5090x86 · Blackwell · recommended32 GB GDDR7$0.69 / hourCheck availabilityDeploy now Qwen3 Coder 30B AWQ 4-bit on RTX 5090
DGX SparkArm · GB10128 GB unified$0.79 / hourCheck availabilityDeploy now Qwen3 Coder 30B AWQ 4-bit on DGX Spark
RTX PRO 6000x86 · Blackwell96 GB GDDR7$1.89 / hourCheck availabilityDeploy now Qwen3 Coder 30B AWQ 4-bit on RTX PRO 6000
H100 SXMx86 · Hopper80 GB HBM3$2.69 / hourCheck availabilityDeploy now Qwen3 Coder 30B AWQ 4-bit on H100 SXM
H200x86 · Hopper141 GB HBM3eDoes not fit: the one-click preset does not run on this GPU.
B200x86 · Blackwell180 GB HBM3eDoes not fit: the one-click preset does not run on this GPU.
B300x86 · Blackwell288 GB HBM3eDoes not fit: the one-click preset does not run on this GPU.

Builds by the model's maker, NVIDIA and Unsloth, read from Hugging Face on 21 November 2026. Memory is an estimate (weights x 1.15 plus 3 GB); GGUF runs on llama.cpp, which GPUwerk builds for the DGX Spark only, and NVFP4 needs a Blackwell GPU. SGLang is not offered: there is no SGLang runtime yet.

Details

About the model.

Qwen3 Coder 30B
MakerQwen
TaskCoding · Text
Parameters30B total, 3B active (mixture of experts)
Context32,768 tokens as served (one-click preset)
LicenceApache 2.0

80.9 tok/s for one request on one DGX Spark, measured by GPUwerk with vLLM on 2 September 2026. Every other speed figure is in the model guide, with its source.

Quick start

  1. Deploy Qwen3 Coder 30B on an RTX 5090. The console opens with the GPU and model picked.
  2. Wait for the instance to show Running: the model server answers once the weights are loaded.
  3. Call the HTTPS endpoint from the instance page with an API key, like any OpenAI-compatible API.
curl https://<your-endpoint>/v1/chat/completions \
  -H "Authorization: Bearer $GPUWERK_API_KEY" -H "Content-Type: application/json" \
  -d '{"model": "qwen3-coder-30b", "messages": [{"role": "user", "content": "Hello"}]}'

SSH, the browser terminal, VNC and your workspace work the same on every instance. Terminate when you are done and billing ends.

Related models

QwenText

Qwen3.6 35B-A3B

A fast mixture-of-experts model for chat and agents, also on the pay-per-token API.

One-click preset · llama.cpp · DGX Spark

OpenAIText

GPT-OSS 120B

OpenAI's open-weight 120B model, quantized to fit one DGX Spark.

One-click preset · llama.cpp · DGX Spark

QwenText

Qwen3.8 Flash Next

A large Qwen3.8 mixture-of-experts model, quantized to fit one DGX Spark.

One-click preset · llama.cpp · DGX Spark

All models in the library