FitMyLLM
Alibaba/Dense

AlibabaQwen3-8B

chat
8.2B
Parameters
40K
Context length
20
Benchmarks
6
Quantizations
9.0M
HF downloads
Architecture
Dense
Released
2025-04-28
Layers
36
KV Heads
8
Head Dim
128
Family
qwen

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.895.5 GBgood
Q5_K_S5.576.2 GBgood
Q5_K_M5.76.3 GBgood
Q6_K6.567.2 GBexcellent
Q8_08.59.2 GBlossless
FP161616.9 GBlossless

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

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN QWEN3-8B NOW

Rent on RunPod →Or Vast.ai →

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

Community Ratings

Loading ratings...

Benchmarks (20)

Arena Elo1462
MATH-50093.2
MATH89.0
HumanEval85.0
IFEval78.0
AIME63.7
AA Math63.7
GPQA Diamond61.2
MMLU-PRO55.0
LiveCodeBench51.3
GPQA45.0
BBH36.6
SciCode20.4
IFBench19.9
AA Intelligence16.4
MUSR15.5
AA Long Context13.0
AA Coding7.8
HLE5.6
Terminal-Bench1.5

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run qwen3:8.2b-instruct-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
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 3050 6GB
6 GB VRAM • 168 GB/s
NVIDIA
$169
AmazonNeweggeBayPCPartPicker
Intel Arc A380
6 GB VRAM • 186 GB/s
INTEL
$129
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 2060 6GB
6 GB VRAM • 336 GB/s
NVIDIA
$150
AmazonNeweggeBayPCPartPicker
NVIDIA GTX 1660 SUPER
6 GB VRAM • 336 GB/s
NVIDIA
$150
AmazonNeweggeBayPCPartPicker
NVIDIA GTX 1660 Ti
6 GB VRAM • 288 GB/s
NVIDIA
$140
AmazonNeweggeBayPCPartPicker
NVIDIA GTX 1060 6GB
6 GB VRAM • 192 GB/s
NVIDIA
$80
AmazonNeweggeBayPCPartPicker
NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA GeForce GTX 1060 6 GB
6 GB VRAM • 192 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 1660
6 GB VRAM • 192 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 1660 SUPER
6 GB VRAM • 336 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce GTX 1660 Ti
6 GB VRAM • 288 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 2060
6 GB VRAM • 336 GB/s
NVIDIA
$140
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 2060 TU104
6 GB VRAM • 336 GB/s
NVIDIA
$140
AmazonNeweggeBayPCPartPicker
AMD Radeon RX 5600 OEM
6 GB VRAM • 288 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon RX 5600 XT
6 GB VRAM • 288 GB/s
AMD
$90
AmazonNeweggeBayPCPartPicker
AMD Radeon RX 5600M
6 GB VRAM • 288 GB/s
AMD
AmazonNeweggeBayPCPartPicker

Find the best GPU for Qwen3-8B

Build Hardware for Qwen3-8B
▸ SPEC SHEET

Qwen3-8B — 8.2B Dense.

▸ SPECIFICATIONS
PARAMETERS
8.2B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
40K tokens
CAPABILITIES
chat
RELEASE DATE
2025-04-28
PROVIDER
Alibaba
FAMILY
qwen
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.895.5 GB94%
Q5_K_S5.576.2 GB96%
Q5_K_M5.76.3 GB96%
Q6_K6.567.2 GB97%
Q8_08.59.2 GB100%
FP161616.9 GB100%
§ 01BENCHMARK SCORES
HumanEval85.0
MMLU-PRO55.0
MATH89.0
IFEval78.0
BBH36.6
GPQA45.0
MUSR15.5
Arena Elo1462.0
GPQA Diamond61.2
LiveCodeBench51.3
AIME63.7
MATH-50093.2
HLE5.6
AA Intelligence16.4
AA Coding7.8
AA Math63.7
aa_ifbench19.9
aa_terminal_bench1.5
aa_scicode20.4
aa_lcr13.0
§ 02RUN COMMAND

Run Qwen3-8B locally with Ollama — needs 5.5 GB VRAM at Q4_K_M:

$ollama run qwen3:8.2b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA RTX 3050 6GB
6 GB · 168 GB/s
Intel Arc A380
6 GB · 186 GB/s
NVIDIA RTX 2060 6GB
6 GB · 336 GB/s
NVIDIA GTX 1660 SUPER
6 GB · 336 GB/s
NVIDIA GTX 1660 Ti
6 GB · 288 GB/s
NVIDIA GTX 1060 6GB
6 GB · 192 GB/s
NVIDIA Tesla C2070
6 GB · 143 GB/s
NVIDIA Tesla C2075
6 GB · 150 GB/s
NVIDIA Tesla C2090
6 GB · 177 GB/s
NVIDIA Tesla M2070
6 GB · 150 GB/s
NVIDIA Tesla M2070-Q
6 GB · 150 GB/s
NVIDIA Tesla M2075
6 GB · 150 GB/s
NVIDIA Tesla M2090
6 GB · 177 GB/s
NVIDIA Tesla X2070
6 GB · 177 GB/s
NVIDIA Tesla X2090
6 GB · 177 GB/s