FITMYLLM·AUGUST 17, 2026·OPEN METHODOLOGY · COMMUNITY BENCHMARKS

LIVE·UPDATED DAILY

Independent benchmarks for self-hosted AI infrastructure.

▸Privacy Shield

Alibaba/Dense

Qwen 3.5 9B

Qwen 3.5 9B — multimodal model with math, coding, vision, and 201 languages.

chatcodingreasoningmultilingualvisionmath

9.65B

Parameters

256K

Context length

18

Benchmarks

6

Quantizations

3.3M

HF downloads

Architecture

Dense

Released

2026-02-01

Layers

32

KV Heads

4

Head Dim

256

Family

qwen

Quantization Options

Context length:

Quant	Bits	VRAM @ 16K	Quality
Q4_K_M	4.89	6.8 GB 6.4 + 0.4 KV	good
Q5_K_S	5.57	7.6 GB 7.2 + 0.4 KV	good
Q5_K_M	5.7	7.7 GB 7.4 + 0.4 KV	good
Q6_K	6.56	8.8 GB 8.4 + 0.4 KV	excellent
Q8_0	8.5	11.1 GB 10.7 + 0.4 KV	lossless
FP16	16	20.2 GB 19.8 + 0.4 KV	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN QWEN 3.5 9B NOW

Rent on Vast.ai →Or RunPod →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (18)

Arena Elo1470

IFEval91.5

MMBench90.1

τ²-Bench86.8

MMLU-PRO82.5

GPQA Diamond80.6

MMMU70.1

IFBench66.7

AA Long Context59.0

MATH48.8

BBH36.6

AA Intelligence32.4

SciCode27.5

AA Coding25.3

Terminal-Bench24.2

MUSR15.5

HLE13.3

GPQA8.9

Run this model

▸Easiest way to get started·Beginners

curl -fsSL https://ollama.com/install.sh | sh

$ollama run qwen3.5:9b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE

>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace Ollama Library GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 4060 Ti 8GB

8 GB VRAM • 288 GB/s

NVIDIA

$399

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 4060

8 GB VRAM • 272 GB/s

NVIDIA

$299

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 3070 Ti

8 GB VRAM • 608 GB/s

NVIDIA

$499

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 3070

8 GB VRAM • 448 GB/s

NVIDIA

$325

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 3060 Ti

8 GB VRAM • 448 GB/s

NVIDIA

$250

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 3050 8GB

8 GB VRAM • 224 GB/s

NVIDIA

$249

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 288 GB/s

AMD

$269

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 280 GB/s

AMD

$399

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 512 GB/s

INTEL

$199

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 68 GB/s

APPLE

$499

8 GB VRAM • 100 GB/s

APPLE

$599

8 GB VRAM • 100 GB/s

APPLE

$599

NVIDIA RTX 2080 SUPER

8 GB VRAM • 496 GB/s

NVIDIA

$280

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 2080

8 GB VRAM • 448 GB/s

NVIDIA

$260

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 2070 SUPER

8 GB VRAM • 448 GB/s

NVIDIA

$240

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 2070

8 GB VRAM • 448 GB/s

NVIDIA

$200

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 2060 SUPER

8 GB VRAM • 448 GB/s

NVIDIA

$180

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GTX 1080

8 GB VRAM • 320 GB/s

NVIDIA

$130

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GTX 1070 Ti

8 GB VRAM • 256 GB/s

NVIDIA

$120

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GTX 1070

8 GB VRAM • 256 GB/s

NVIDIA

$100

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 3060 8GB

8 GB VRAM • 224 GB/s

NVIDIA

$280

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 256 GB/s

AMD

$200

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 224 GB/s

AMD

$165

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 448 GB/s

AMD

$150

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 448 GB/s

AMD

$130

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

8 GB VRAM • 512 GB/s

INTEL

$179

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 5060 Ti 8GB

8 GB VRAM • 448 GB/s

NVIDIA

$379

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 5060

8 GB VRAM • 448 GB/s

NVIDIA

$299

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA Tesla K8

8 GB VRAM • 160 GB/s

NVIDIA

NVIDIA Tesla M60

8 GB VRAM • 160 GB/s

NVIDIA

Find the best GPU for Qwen 3.5 9B

Build Hardware for Qwen 3.5 9B

Model Card

View on HuggingFace

Qwen 3.5 9B — multimodal model with math, coding, vision, and 201 languages.

▸ SPEC SHEET

Qwen 3.5 9B — 9.65B Dense.

▸ SPECIFICATIONS

PARAMETERS: 9.65B
ARCHITECTURE: Dense Transformer
CONTEXT LENGTH: 256K tokens
CAPABILITIES: chat, coding, reasoning, multilingual, vision, math
RELEASE DATE: 2026-02-01
PROVIDER: Alibaba
FAMILY: qwen

▸ VRAM REQUIREMENTS

QUANT	BPW	VRAM	QUALITY
Q4_K_M	4.89	6.4 GB	94%
Q5_K_S	5.57	7.2 GB	96%
Q5_K_M	5.7	7.4 GB	96%
Q6_K	6.56	8.4 GB	97%
Q8_0	8.5	10.7 GB	100%
FP16	16	19.8 GB	100%

§ 01BENCHMARK SCORES

MMLU-PRO82.5

MATH48.8

IFEval91.5

BBH36.6

MMMU70.1

MUSR15.5

MMBench90.1

Arena Elo1470.0

GPQA Diamond80.6

HLE13.3

AA Intelligence32.4

AA Coding25.3

GPQA8.9

aa_ifbench66.7

aa_terminal_bench24.2

aa_tau286.8

aa_scicode27.5

aa_lcr59.0

§ 02RUN COMMAND

Run Qwen 3.5 9B locally with Ollama — needs 6.4 GB VRAM at Q4_K_M:

$ollama run qwen3.5:9b

§ 03COMPATIBLE GPUs

30 @ Q4_K_M

NVIDIA RTX 4060 Ti 8GB

8 GB · 288 GB/s

NVIDIA RTX 4060

8 GB · 272 GB/s

NVIDIA RTX 3070 Ti

8 GB · 608 GB/s

NVIDIA RTX 3070

8 GB · 448 GB/s

NVIDIA RTX 3060 Ti

8 GB · 448 GB/s

NVIDIA RTX 3050 8GB

8 GB · 224 GB/s

8 GB · 288 GB/s

8 GB · 280 GB/s

8 GB · 512 GB/s

8 GB · 68 GB/s

8 GB · 100 GB/s

8 GB · 100 GB/s

NVIDIA RTX 2080 SUPER

8 GB · 496 GB/s

NVIDIA RTX 2080

8 GB · 448 GB/s

NVIDIA RTX 2070 SUPER

8 GB · 448 GB/s