Qwen 2.5

What Qwen 2.5 is for

Qwen 2.5 is trained for code. Alibaba released it in 2024-09 with 7 sizes (0.5B, 1.5B, 3B, 7B, 14B, 32B, 72B), 128K of context and a Apache 2.0 (most sizes) licence. Context length matters more here than for chat, because a coding assistant that cannot see the whole file is guessing. The catalogue records its strength as strongest 7B-32B on consumer hardware, and it is the class of model an editor plugin such as Continue or Tabby points at.

Sizes and memory

The 7B needs about 5 GB of weights at Q4_K_M and the 72B about 44 GB, a spread of 39 GB across the family. The catalogue's default pick is 7B. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.

Size	Weights at Q4_K_M	Recommended VRAM	Smallest card in our guide that holds it
7B	5 GB	8 GB	NVIDIA Jetson Orin Nano 8GB
14B	9 GB	14 GB	NVIDIA RTX 3060 12GB
32B	20 GB	30 GB	NVIDIA RTX 3090
72B	44 GB	66 GB	Apple M3 Ultra

Hardware that runs Qwen 2.5

Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of Qwen 2.5 at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 7B.

The largest size any of them holds is the 72B at 44 GB, on the Apple M3 Ultra (192 GB at 800 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.

What people use it for

The catalogue lists 5 recorded uses for Qwen 2.5: chat, code, RAG, agentic, multilingual. It is tagged chat, instruction, code, multilingual, tools.

Where Qwen 2.5 sits in the Qwen family

Our catalogue holds 5 Qwen entries. Ordered by release date, Qwen 2.5 (2024-09) is the 1st of them, and Qwen 3 VL (2025-10) is newer. Qwen 2.5-Coder and Qwen 3 carry the same recorded memory footprint, so choosing between those and this one is a question of behaviour rather than of hardware: Qwen 2.5 is the one recorded here for strongest 7B-32B on consumer hardware.

The Apache 2.0 (most sizes) licence puts no usage ceiling on it, which matters if the thing you are building has users. That is the practical difference between this and a vendor community licence.

Context window: 128K

128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.

How to run Qwen 2.5 locally

Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.

Option 1: Ollama (simplest)

# find the tag for Qwen 2.5 at ollama.com/library
ollama run <tag>

Option 2: Mullama (production)

mullama pull <tag>
mullama run <tag>

Option 3: llama.cpp (CLI)

# download a GGUF from Hugging Face, searching for "Qwen 2.5 GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

Sources

Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.