Qwen3.5 27B: Local LLM VRAM Requirements

About Qwen3.5 27B

Qwen3.5 27B is a dense model with 27.78B parameters, built from 64 layers with a hidden size of 5120. Its repository was published on 2026-02-24. The license listed on Hugging Face is apache-2.0. Most of its layers are linear-attention layers that keep a small fixed state, so only 16 of 64 grow with the window and long contexts cost far less than on a conventional model.

Memory needed, by quantization

At an 8k context window. Quality is our rough ranking of how much the compression costs you: anything at or above Q5 is hard to tell apart from the original in normal use.

Quantization	File size	KV cache	Total VRAM	Quality	What it costs you
Q8_0	27.49 GB	0.64 GB	27.32 GB	99%	Lossless in practice. Use it when the memory is there.
Q6_K	21.22 GB	0.64 GB	21.33 GB	98%	Very close to Q8 for two thirds of the size.
Q5_K_M	18.4 GB	0.64 GB	18.64 GB	96%	The quality-first choice when Q6 will not fit.
Q4_K_M	15.62 GB	0.64 GB	15.99 GB	93%	The default. Best size-to-quality ratio for local use.
IQ4_XS	13.74 GB	0.64 GB	14.2 GB	91%	Importance-matrix 4-bit. Q4_K_S quality, smaller file.
Q3_K_M	12.65 GB	0.64 GB	13.15 GB	86%	Degradation starts to show. A way to fit one size up.
IQ3_XXS	9.9 GB	0.64 GB	10.53 GB	79%	Aggressive. Only worth it on very large models.

What a longer conversation costs

Same model at Q4_K_M, only the context window changes. This model mixes 48 linear-attention layers, which keep only a small fixed state, with 16 ordinary layers, so its cache grows far more slowly than a conventional model of the same depth.

Context	KV cache	Total VRAM	Fits in 8 GB	Fits in 12 GB	Fits in 24 GB
4k	0.39 GB	15.74 GB	no	no	yes
8k	0.64 GB	15.99 GB	no	no	yes
16k	1.14 GB	16.49 GB	no	no	yes
32k	2.14 GB	17.49 GB	no	no	yes
64k	4.14 GB	19.49 GB	no	no	yes
128k	8.14 GB	23.49 GB	no	no	no

The "fits" columns allow for the roughly 0.8 GB Windows keeps for the desktop.

Which hardware runs Qwen3.5 27B

59 of 118 consumer devices run it at a quantization worth using, at an 8k context window. Another 16 can load it only by compressing the weights far enough to damage the model, marked with a warning below.

Device	Memory	Verdict	Quantization	Used	Speed
GeForce RTX 5090 NVIDIA	32 GB	Runs great	Q8_0	27.32 GB	49.1 t/s
RTX PRO 6000 Blackwell NVIDIA	96 GB	Runs great	Q8_0	27.32 GB	49.1 t/s
RTX 6000 Ada Generation NVIDIA	48 GB	Runs great	Q8_0	27.32 GB	26.3 t/s
RTX A6000 NVIDIA	48 GB	Runs well	Q8_0	27.32 GB	21 t/s
Apple M3 Ultra 96GB Apple	96 GB	Runs well	Q8_0	28.54 GB	20.7 t/s
Apple M3 Ultra 256GB Apple	256 GB	Runs well	Q8_0	28.54 GB	20.7 t/s
Apple M3 Ultra 512GB Apple	512 GB	Runs well	Q8_0	28.54 GB	20.7 t/s
Apple M1 Ultra 64GB Apple	64 GB	Runs well	Q8_0	28.54 GB	20.2 t/s
Apple M1 Ultra 128GB Apple	128 GB	Runs well	Q8_0	28.54 GB	20.2 t/s
Apple M2 Ultra 64GB Apple	64 GB	Runs well	Q8_0	28.54 GB	20.2 t/s
Apple M2 Ultra 128GB Apple	128 GB	Runs well	Q8_0	28.54 GB	20.2 t/s
Apple M2 Ultra 192GB Apple	192 GB	Runs well	Q8_0	28.54 GB	20.2 t/s
Radeon PRO W7900 AMD	48 GB	Runs well	Q8_0	27.32 GB	20.1 t/s
GeForce RTX 4090 NVIDIA	24 GB	Runs great	Q6_K	21.33 GB	35.5 t/s
GeForce RTX 3090 Ti NVIDIA	24 GB	Runs great	Q6_K	21.33 GB	35.5 t/s
GeForce RTX 3090 NVIDIA	24 GB	Runs great	Q6_K	21.33 GB	33 t/s
GeForce RTX 5090 Laptop NVIDIA	24 GB	Runs great	Q6_K	21.33 GB	31.6 t/s
Radeon RX 7900 XTX AMD	24 GB	Runs great	Q6_K	21.33 GB	28.7 t/s
RTX A5000 NVIDIA	24 GB	Runs great	Q6_K	21.33 GB	27.1 t/s
Radeon RX 7900 XT AMD	20 GB	Just fits	Q5_K_M	18.64 GB	27.4 t/s
Apple M4 Max 48GB Apple	48 GB	Runs well	Q8_0	28.54 GB	13.8 t/s
Apple M4 Max 64GB Apple	64 GB	Runs well	Q8_0	28.54 GB	13.8 t/s
Apple M4 Max 128GB Apple	128 GB	Runs well	Q8_0	28.54 GB	13.8 t/s
GeForce RTX 5080 NVIDIA	16 GB	Runs great	IQ4_XS	14.2 GB	51.3 t/s
GeForce RTX 5070 Ti NVIDIA	16 GB	Runs great	IQ4_XS	14.2 GB	47.9 t/s

Show 35 more devices

GeForce RTX 5080 Laptop NVIDIA	16 GB	Runs great	IQ4_XS	14.2 GB	41.1 t/s
GeForce RTX 4080 SUPER NVIDIA	16 GB	Runs great	IQ4_XS	14.2 GB	39.4 t/s
GeForce RTX 4080 NVIDIA	16 GB	Runs great	IQ4_XS	14.2 GB	38.3 t/s
GeForce RTX 4070 Ti SUPER NVIDIA	16 GB	Runs great	IQ4_XS	14.2 GB	35.9 t/s
GeForce RTX 4090 Laptop NVIDIA	16 GB	Runs great	IQ4_XS	14.2 GB	30.8 t/s
Radeon RX 9070 XT AMD	16 GB	Runs great	IQ4_XS	14.2 GB	29.3 t/s
Radeon RX 9070 AMD	16 GB	Runs great	IQ4_XS	14.2 GB	29.3 t/s
Radeon RX 7800 XT AMD	16 GB	Runs great	IQ4_XS	14.2 GB	28.3 t/s
Radeon RX 7900 GRE AMD	16 GB	Runs great	IQ4_XS	14.2 GB	26.1 t/s
GeForce RTX 5060 Ti 16GB NVIDIA	16 GB	Runs well	IQ4_XS	14.2 GB	24 t/s
RTX A4000 NVIDIA	16 GB	Runs well	IQ4_XS	14.2 GB	24 t/s
Radeon RX 6900 XT AMD	16 GB	Runs well	IQ4_XS	14.2 GB	23.2 t/s
Radeon RX 6800 AMD	16 GB	Runs well	IQ4_XS	14.2 GB	23.2 t/s
Arc A770 16GB Intel	16 GB	Runs well	IQ4_XS	14.2 GB	23.1 t/s
GeForce RTX 4060 Ti 16GB NVIDIA	16 GB	Runs well	IQ4_XS	14.2 GB	15.4 t/s
Apple M1 Max 64GB Apple	64 GB	Runs well	Q8_0	28.54 GB	10.1 t/s
Apple M2 Max 64GB Apple	64 GB	Runs well	Q8_0	28.54 GB	10.1 t/s
Apple M2 Max 96GB Apple	96 GB	Runs well	Q8_0	28.54 GB	10.1 t/s
Apple M3 Max 48GB Apple	48 GB	Runs well	Q8_0	28.54 GB	10.1 t/s
Apple M3 Max 64GB Apple	64 GB	Runs well	Q8_0	28.54 GB	10.1 t/s
Apple M3 Max 96GB Apple	96 GB	Runs well	Q8_0	28.54 GB	10.1 t/s
Apple M3 Max 128GB Apple	128 GB	Runs well	Q8_0	28.54 GB	10.1 t/s
NVIDIA DGX Spark 128GB NVIDIA	128 GB	Runs well	Q5_K_M	19.49 GB	11 t/s
Apple M4 Pro 48GB Apple	48 GB	Runs well	Q5_K_M	19.46 GB	10.2 t/s
Apple M4 Pro 64GB Apple	64 GB	Runs well	Q5_K_M	19.46 GB	10.2 t/s
Radeon RX 7600 XT AMD	16 GB	Runs well	IQ4_XS	14.2 GB	13.1 t/s
Jetson AGX Orin 32GB NVIDIA	32 GB	Runs well	IQ4_XS	14.83 GB	11 t/s
Jetson AGX Orin 64GB NVIDIA	64 GB	Runs well	IQ4_XS	14.83 GB	11 t/s
Ryzen AI Max+ 395 32GB AMD	32 GB	Runs well	IQ4_XS	14.83 GB	10.6 t/s
Ryzen AI Max+ 395 64GB AMD	64 GB	Runs well	IQ4_XS	14.83 GB	10.6 t/s
Ryzen AI Max+ 395 96GB AMD	96 GB	Runs well	IQ4_XS	14.83 GB	10.6 t/s
Ryzen AI Max+ 395 128GB AMD	128 GB	Runs well	IQ4_XS	14.83 GB	10.6 t/s
GeForce RTX 3080 Ti NVIDIA	12 GB	Just fits	IQ3_XXS !	10.53 GB	66.5 t/s
GeForce RTX 3080 12GB NVIDIA	12 GB	Just fits	IQ3_XXS !	10.53 GB	66.5 t/s
GeForce RTX 5070 NVIDIA	12 GB	Just fits	IQ3_XXS !	10.53 GB	49 t/s

Can my GPU run Qwen3.5 27B?

A direct answer for popular devices, each with the settings we would use.

How it compares

Other models in the same family or of a similar size, on a 12 GB card and a 24 GB card, each at the best quantization that fits.

Model	Weights at 4 bits	GeForce RTX 3060 12GB	GeForce RTX 4090
Qwen3.5 27B	15.6 GB	does not fit well	35.5 t/s at Q6_K
Qwen3 30B A3B	17.2 GB	36.3 t/s at Q4_K_M	146.3 t/s at Q5_K_M
Qwen3 Coder 30B A3B Instruct	17.2 GB	36.3 t/s at Q4_K_M	146.3 t/s at Q5_K_M
Qwen3 32B	18.4 GB	does not fit well	37.1 t/s at Q4_K_M
Gemma 4 31B Instruct	17.6 GB	does not fit well	35.5 t/s at Q4_K_M
Gemma 4 26B A4B Instruct	14.5 GB	37.6 t/s at Q4_K_M	117 t/s at Q6_K

What to buy to run Qwen3.5 27B

The cheapest hardware that runs it at a quantization worth using and a speed you would not resent, at an 8k context window.

Cheapest that works

Arc A770 16GB

$280 used

IQ4_XS · uses 14.2 GB of its 16 GB · about 23.1 tokens/s

Best value

Radeon RX 6800

$330 used

IQ4_XS · about 23.2 tokens/s · 512 GB/s

Device	Price	Memory	Runs it at	Speed
Arc A770 16GB Intel	$280 used	16 GB	IQ4_XS	23.1 t/s	Check price
Radeon RX 6800 AMD	$330 used	16 GB	IQ4_XS	23.2 t/s	Check price
GeForce RTX 5060 Ti 16GB NVIDIA	$430	16 GB	IQ4_XS	24 t/s	Check price
Radeon RX 7800 XT AMD	$480	16 GB	IQ4_XS	28.3 t/s	Check price
Radeon RX 9070 AMD	$560	16 GB	IQ4_XS	29.3 t/s	Check price
Radeon RX 7900 XT AMD	$650	20 GB	Q5_K_M	27.4 t/s	Check price
GeForce RTX 3090 NVIDIA	$700 used	24 GB	Q6_K	33 t/s	Check price
GeForce RTX 4070 Ti SUPER NVIDIA	$750	16 GB	IQ4_XS	35.9 t/s	Check price

Indicative prices reviewed 2026-09-01; used prices are marketplace typical. Options that cost more than a cheaper one with no more memory and no more speed are hidden. Price links are Amazon affiliate links. Change the standard, the context window or the budget in the buying tool.

These numbers also cover

Fine-tunes share their base model's architecture, so they need exactly the same memory. If you are looking for one of these, the figures above apply unchanged.

OBLITERATUS/Qwen3.8-27B-OBLITERATED

Where it sits in the catalog

Source: Qwen/Qwen3.5-27B on Hugging Face. Downloaded 2.5M times in the last month. Published 2026-02-24. Architecture figures are read from the repository's own configuration file, so they move when the model does.

Qwen3 30B A3B

30.53B (3.34B active) · 40k context

Qwen3 Coder 30B A3B Instruct

30.53B (3.34B active) · 40k context

Qwen3 32B

32.76B · 40k context

Qwen2.5 32B Instruct

32.76B · 32k context

Qwen2.5 Coder 32B Instruct

32.76B · 32k context

Qwen3.5 35B A3B

35.95B (2.9B active) · 256k context

Qwen3 14B

14.77B · 40k context

Qwen2.5 14B Instruct

14.77B · 32k context

Questions people ask about Qwen3.5 27B

How much VRAM does Qwen3.5 27B need?

At Q4_K_M with an 8k context window, Qwen3.5 27B needs about 15.99 GB: 14.91 GB of weights, 0.64 GB of KV cache and 0.44 GB of overhead. At the highest-quality file it needs about 27.32 GB.

What is the cheapest GPU that runs Qwen3.5 27B?

The smallest consumer device in our catalog that fits it is the GeForce RTX 5080 with 16 GB, running it at IQ4_XS at roughly 51.3 tokens per second.

How much does a longer context window add for Qwen3.5 27B?

On the memory side, a 32k window adds 2.1 GB of KV cache on top of the weights, and the cache grows more slowly than a conventional model because of its attention design. The longest window the model supports natively is 256k tokens.