Alibaba Cloud2B~2 GB VRAM at Q4_K_M

Qwen 3.5 2B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

Compact dense model with strong reasoning for its size. Runs on any modern device with 4 GB RAM. Good balance of speed and intelligence for assistants, summarization, and simple coding tasks.

Qwen 3.5 2B needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic73
Creative70
Coding71

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
1.5 GB~277 tok/sFits
Q3_K_M
3.41 bpw
1.7 GB~259 tok/sFits
Q4_K_M
4.83 bpw
2 GB~231 tok/sFits
Q5_K_M
5.67 bpw
2.2 GB~217 tok/sFits
Q6_K
6.56 bpw
2.4 GB~204 tok/sFits
Q8_0
8.50 bpw
2.9 GB~180 tok/sFits
F16
16.00 bpw
4.8 GB~125 tok/sFits

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Qwen 3.5 2B VRAM calculator →

Get Qwen 3.5 2B running

The cheapest catalogued GPU that runs Qwen 3.5 2B is the Intel Arc B570 (10 GB).

Buy this hardware Intel Arc B570 10GB — 10 GB VRAM · 150 W board powerDeploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.

How to run Qwen 3.5 2B

Install Ollama, then run:

ollama run qwen3.5:2b
Weights on Hugging Face: Qwen/Qwen3.5-2B-Instruct ↗

Specifications

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Parameters
2 Billion
Context window
256,000
Architecture
Dense Transformer (Gated DeltaNet)
Provider
Alibaba Cloud
Licence
Apache 2.0
Practical deployment
Edge device (phone, SBC)
Specified at
Q4_K_M
System RAM
6 GB
Record updated
2026-02-15
LicenceApache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best formobileedge devicessummarizationquick chat

Can I run Qwen 3.5 2B on my GPU?

Other Qwen 3.5 sizes

Qwen 3.5 2B — frequently asked questions

How much VRAM does Qwen 3.5 2B need?

About 2 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Qwen 3.5 2B run on an RTX 4090 (24 GB)?

Yes. Qwen 3.5 2B needs about 2 GB at Q4_K_M, inside a 24 GB card, at an estimated 231 tokens/sec.

How do I run Qwen 3.5 2B locally?

Install Ollama and run `ollama run qwen3.5:2b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Qwen 3.5 come in?

Qwen 3.5 0.8B (1 GB), Qwen 3.5 2B (2 GB), Qwen 3.5 4B (3 GB), Qwen 3.5 9B (6 GB), Qwen 3.5 27B (17 GB), Qwen 3.5 35B-A3B (22 GB), Qwen 3.5 122B-A10B (74 GB), Qwen 3.5 397B-A17B (240 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.