Yes — with 23.8 GB to spare

Qwen2.5-Coder 32B at Q4_K_M fits your 2× GeForce RTX 3090 entirely on the GPUs at 8K context, at an estimated 31 tokens per second. Past 103K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully on GPU 8K context Q4_K_M · 18.4 GB Apache 2.0 Released Nov 2024

The first local code model that felt competitive with hosted assistants. Qwen3.8 27B is smaller and far ahead on agentic work.

Hardware requirements What hardware do I need to run Qwen2.5-Coder 32B? →

At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 36 GB Mac (M4 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 18.4 GB
Weights 18.4 GB KV cache @ 8K 2.00 GB Runtime overhead 0.6 GB Free 23.8 GB of 44.8 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 32.5 GB 35.1 GB 46K 17 −0.1% ppl Long context
Q6_K 25.0 GB 27.6 GB 76K 23 −0.4% ppl Long context
Q5_K_M 21.7 GB 24.3 GB 90K 26 −0.8% ppl Long context
Q4_K_M 18.4 GB 21.0 GB 103K 31 −1.9% ppl Recommended
Q3_K_M 14.9 GB 17.5 GB 117K 38 −5.4% ppl Long context
Q2_K 12.8 GB 15.4 GB 125K 44 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ ollama pull qwen2.5-coder:32b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run qwen2.5-coder:32b

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

01Download is 18.4 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02llama.cpp and Ollama spread the layers over both cards on their own. The cards take turns on every token, so expect about one card's speed; vLLM's --tensor-parallel-size 2 runs them in parallel instead.
03There is room to go to 103K context on this card.
See all models for this rig Compare with another model

Related models on a 2× GeForce RTX 3090

ModelTotalTok/s est.
Qwen2.5-Coder 14B
14.8B · same family
Q4_K_M · 10.4 GB 68 Runs great
Qwen2.5-Coder 7B
7.62B · same family
Q4_K_M · 5.3 GB 132 Runs great
Qwen3 32B
32.8B · similar size
Q4_K_M · 21.0 GB 31 Runs great
DeepSeek-R1-Distill-Qwen 32B
32.8B · similar size
Q4_K_M · 21.0 GB 31 Runs great
LLM-jp 4 33B Thinking
33.2B · similar size
Q4_K_M · 21.3 GB 30 Runs great
Olmo 3.1 32B Instruct
32.2B · similar size
Q4_K_M · 20.0 GB 31 Runs great
Nemotron 3.5 Lightning 30B-A3B
31.6B MoE · similar size
Q4_K_M · 18.4 GB 121 Runs great

Every model against the 2× GeForce RTX 3090 →

Qwen2.5-Coder 32B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
21.0 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
21.0 GB ~3.1 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
21.0 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
21.0 GB 33 Tight fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
21.0 GB 32 Tight fit
GeForce RTX 5090
30.4 GB usable · 1792 GB/s
21.0 GB 59 Runs great
M4 Max · 36 GB
27.0 GB usable · 410 GB/s
21.0 GB 12 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
21.0 GB 12 Runs great

All 114 devices, by tier →