Alibaba Cloud27B~17 GB VRAM at Q4_K_M

Qwen 3.5 27B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

Best dense model under 24 GB VRAM. Needs ~16.5 GB at Q4_K_M, fitting on a single RTX 3090 or 4090. Strong all-rounder for long-document analysis, multilingual work, and complex reasoning with ~256K context (extensible to ~1M via YaRN). An FP8 release is also available.

Qwen 3.5 27B needs about 17 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.

Logic90
Creative88
Coding89

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 Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.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
9.7 GB~66 tok/sFits
Q3_K_M
3.41 bpw
12.3 GB~54 tok/sFits
Q4_K_M
4.83 bpw
17.1 GB~40 tok/sFits
Q5_K_M
5.67 bpw
19.9 GB~35 tok/sFits
Q6_K
6.56 bpw
22.9 GB~31 tok/sTight
Q8_0
8.50 bpw
29.5 GB~4 tok/sOffload
F16
16.00 bpw
54.8 GB~2 tok/sOffload

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Qwen 3.5 27B VRAM calculator →

Get Qwen 3.5 27B running

The cheapest catalogued GPU that runs Qwen 3.5 27B is the AMD Radeon RX 7900 XT (20 GB).

Buy this hardware AMD Radeon RX 7900 XT 20GB — 20 GB VRAM · 315 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.
AMD Radeon RX 7900 XT 20GB
20 GB VRAM · 315 W board power
2026 prices are volatile — check the current listing.

How to run Qwen 3.5 27B

Install Ollama, then run:

ollama run qwen3.5:27b
Weights on Hugging Face: Qwen/Qwen3.5-27B-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
27.8 Billion
Context window
262,144
Architecture
Dense Transformer (Gated DeltaNet)
Provider
Alibaba Cloud
Licence
Apache 2.0
Practical deployment
Single consumer GPU
Specified at
Q4_K_M
System RAM
32 GB
Record updated
2026-02-24
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 forlong documentsreasoningmultilingualanalysis

Can I run Qwen 3.5 27B on my GPU?

Other Qwen 3.5 sizes

Qwen 3.5 27B — frequently asked questions

How much VRAM does Qwen 3.5 27B need?

About 17 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 27B run on an RTX 4090 (24 GB)?

Yes. Qwen 3.5 27B needs about 17 GB at Q4_K_M, inside a 24 GB card, at an estimated 40 tokens/sec.

How do I run Qwen 3.5 27B locally?

Install Ollama and run `ollama run qwen3.5:27b`. 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.