Qwen2.5-Coder-32B-Instruct

alibaba/qwen2.5-coder-32b-instruct

Maker: Alibaba (Qwen), China
Released: 2024-11-12
Family: qwen
Weights: open (apache-2.0)
Tasks: text.chat
Cheapest offering: OpenRouter, about $0.001013 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
OpenRouter	`qwen/qwen-2.5-coder-32b-instruct`	ga	Input: $0.66 Output: $1 Since 2026-11-03 · models.dev, MIT	none	Context: 32,768 tokens Max output: 29,491 tokens	`input.text` claimed `output.text` claimed

Run it locally

Free on your own device. Memory is the weights, the KV cache at the context shown and about 10% overhead; a longer context needs more. GB are 10⁹ bytes. See local models.

Runtime	Model id in the runtime	Quantization	Needs	Context
llama.cpp	`lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF:Q4_K_M`	Q4_K_M	Memory: 24.2 GB at 8,192 tokens GPU memory: 24.2 GB Disk: 19.86 GB Parameters: 32.8B License: apache-2.0	Context: 32,768 tokens
llama.cpp	`lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF:Q6_K`	Q6_K	Memory: 31.94 GB at 8,192 tokens GPU memory: 31.94 GB Disk: 26.89 GB Parameters: 32.8B License: apache-2.0	Context: 32,768 tokens
llama.cpp	`lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF:Q8_0`	Q8_0	Memory: 40.67 GB at 8,192 tokens GPU memory: 40.67 GB Disk: 34.83 GB Parameters: 32.8B License: apache-2.0	Context: 32,768 tokens
LM Studio	`lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF/Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf`	Q4_K_M	Memory: 24.2 GB at 8,192 tokens GPU memory: 24.2 GB Disk: 19.86 GB Parameters: 32.8B License: apache-2.0	Context: 32,768 tokens
LM Studio	`lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF/Qwen2.5-Coder-32B-Instruct-Q6_K.gguf`	Q6_K	Memory: 31.94 GB at 8,192 tokens GPU memory: 31.94 GB Disk: 26.89 GB Parameters: 32.8B License: apache-2.0	Context: 32,768 tokens
LM Studio	`lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF/Qwen2.5-Coder-32B-Instruct-Q8_0.gguf`	Q8_0	Memory: 40.67 GB at 8,192 tokens GPU memory: 40.67 GB Disk: 34.83 GB Parameters: 32.8B License: apache-2.0	Context: 32,768 tokens
Ollama	`qwen2.5-coder:32b`	Q4_K_M	Memory: 24.92 GB at 8,192 tokens GPU memory: 24.92 GB Disk: 20.5 GB Parameters: 32.8B License: apache-2.0	Context: 32,768 tokens

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:aider_polyglot`	0.186	0.1640	2024-11-21	Epoch AI, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

qwen/qwen-2.5-coder-32b-instruct

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/alibaba/qwen2.5-coder-32b-instruct' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=openrouter' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).