Can an RTX 4090 run Qwen2.5-3B-Instruct?

Yes, with room to spare Qwen2.5-3B-Instruct at Q4_K_M needs 2.37 GiB–2.80 GiB at 8,192 tokens of context. The RTX 4090 has about 22 GiB usable.

File: qwen2.5-3b-instruct-q4_k_m.gguf (2.1 GB).

These are estimates from the model's config and file sizes, not measurements. How we calculate

How much room is left

Other files on this GPU

QuantFile sizeEngineTotalFit
BF16 safetensors6.2 GBvllm6.7 GiB–8.5 GiBRuns comfortably
GGUF Q8_03.6 GBllama.cpp3.8 GiB–4.2 GiBRuns comfortably
GGUF Q6_K (Qwen)2.8 GBllama.cpp3.0 GiB–3.5 GiBRuns comfortably
GGUF Q5_K_M2.4 GBllama.cpp2.7 GiB–3.1 GiBRuns comfortably
GGUF Q4_K_M This page2.1 GBllama.cpp2.4 GiB–2.8 GiBRuns comfortably

Same context (8,192 tokens), one chat at a time, each file with its usual engine.

Settings used

Technical identifiers and share data
  • Modelqwen2.5-3b-instruct
  • Hardwarenvidia-geforce-rtx-4090-24gb-desktop
  • Quantizationgguf-q4_k_m
  • Share fragment for this identityv2.eyJzY2hlbWFWZXJzaW9uIjoyLCJjYWxjdWxhdG9yVmVyc2lvbiI6IjAuMy4wIiwiZGF0YXNldFZlcnNpb24iOiIyMDI2LTEwLTAyLjEiLCJjb25maWciOnsibW9kZWxJZCI6InF3ZW4yLjUtM2ItaW5zdHJ1Y3QiLCJoYXJkd2FyZUlkIjoibnZpZGlhLWdlZm9yY2UtcnR4LTQwOTAtMjRnYi1kZXNrdG9wIiwiZGV2aWNlQ291bnQiOjEsInF1YW50aXphdGlvbklkIjoiZ2d1Zi1xNF9rX20iLCJjb250ZXh0VG9rZW5zIjo4MTkyLCJjb25jdXJyZW50U2VxdWVuY2VzIjoxLCJlbmdpbmUiOiJsbGFtYS5jcHAiLCJrdlR5cGUiOiJmcDE2In19
How this number is calculated

Total = weight file + KV cache + runtime buffers. The range spans low to high runtime overhead for the engine shown.

Weights (file)
1.96 GiB (2,104,932,768 bytes)
KV cache
0.28 GiB (301,989,888 bytes)
Runtime buffers
0.13 GiB–0.56 GiB
Total
2.37 GiB–2.80 GiB
Usable memory
22.00 GiB
OS / display reserve
2.00 GiB
Left over
19.20 GiB–19.63 GiB

2.80 GiB high estimate vs 22.00 GiB net

Enough memory does not mean this engine, quant, and OS will run. Support does not mean it will be fast.

  • Requested context is within the recorded native window of 32768 tokens.
  • Full-resident weight estimates use total parameters, including inactive MoE experts.
  • Weight bytes come from the selected weight files only, not from every file in the repository.
  • Download file size is not peak GPU memory. Runtime layout, allocator padding, and KV are extra.
  • Counted files: qwen2.5-3b-instruct-q4_k_m.gguf.
  • Context budget is the number of cached tokens per sequence (prompt plus reserved generation).
  • Concurrent sequences share one model replica; weights are not multiplied by sequence count.
  • KV dtype is independent of weight quantization unless you change it.
Open this combo in the calculatorKV cache

Related pages

Sources

Calculator

This combo page keeps the route model and device. Customize to change them on the main calculator; the share then keeps that identity.

Loading catalog snapshot…

Context length

Longer context needs more memory for the KV cache, the model's working memory for the conversation.

More options
Quantization
Runtime

Engine and KV cache type for this estimate.

Workload

Overhead scenario and the prefill workspace.

Topology

How the model is split across devices. Memory is not added together.

Replica count is an advanced deployment option. Quantity is nodes or GPUs, not replicas.

Budget

System reserve and safety margin. An empty number keeps the previous value.

GiB (2^30 bytes)

%

Custom model

Import a config or type the architecture. Nothing is scanned until you import.

Parsed in the browser. The file is not uploaded.

Only huggingface.co, config.json, no token. Private repos are rejected.

Pick a model to see how much memory it needs.