FitMyLLM
Alibaba/Mixture of Experts

AlibabaQwen3.5-397B-A17B

Flagship Qwen3.5. 397B MoE (17B active). 256K context. 201 languages. Apache 2.0.

chatcodingreasoningvisionmultilingual
397B
Parameters (17B active)
256K
Context length
14
Benchmarks
17
Quantizations
Architecture
MoE
Released
2026-02-01
Layers
60
KV Heads
2
Head Dim
256
Family
qwen

Quantization Options

QuantBitsVRAMQuality
IQ2_XXS2.38118.6 GBlow
IQ2_M2.93145.9 GBlow
Q2_K3.16157.3 GBlow
IQ3_XXS3.25161.8 GBlow
IQ3_XS3.5174.2 GBlow
Q3_K_S3.64181.1 GBlow
IQ3_M3.76187.1 GBlow
Q3_K_M4199.0 GBlow
Q3_K_L4.3213.9 GBmoderate
IQ4_XS4.46221.8 GBmoderate
Q4_K_S4.67232.2 GBmoderate
Q4_K_M4.89243.2 GBgood
Q5_K_S5.57276.9 GBgood
Q5_K_M5.7283.4 GBgood
Q6_K6.56326.0 GBexcellent
Q8_08.5422.3 GBlossless
FP1616794.5 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 QWEN3.5-397B-A17B 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 (14)

τ²-Bench95.6
IFEval92.6
AIME91.3
GPQA Diamond88.4
MMLU-PRO87.8
LiveCodeBench83.6
IFBench78.8
SWE-bench76.4
AA Long Context65.7
AA Intelligence45.0
SciCode42.0
AA Coding41.3
Terminal-Bench40.9
HLE28.7

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run qwen3.5:397b-a17b-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.

AMD Radeon Instinct MI325X
288 GB VRAM • 10300 GB/s
AMD
$20000
AMD Radeon Instinct MI350X
288 GB VRAM • 8190 GB/s
AMD
$25000
AMD Radeon Instinct MI355X
288 GB VRAM • 8190 GB/s
AMD
$30000
Apple M4 Ultra (384GB)
384 GB VRAM • 1092 GB/s
APPLE
$9999
Apple M5 Ultra (384GB)
384 GB VRAM • 1228 GB/s
APPLE

Find the best GPU for Qwen3.5-397B-A17B

Build Hardware for Qwen3.5-397B-A17B
▸ SPEC SHEET

Qwen3.5-397B-A17B — 397B MoE.

▸ SPECIFICATIONS
PARAMETERS
397B (17B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
256K tokens
CAPABILITIES
chat, coding, reasoning, vision, multilingual
RELEASE DATE
2026-02-01
PROVIDER
Alibaba
FAMILY
qwen
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ2_XXS2.38118.6 GB65%
IQ2_M2.93145.9 GB75%
Q2_K3.16157.3 GB78%
IQ3_XXS3.25161.8 GB82%
IQ3_XS3.5174.2 GB84%
Q3_K_S3.64181.1 GB85%
IQ3_M3.76187.1 GB86%
Q3_K_M4199.0 GB88%
Q3_K_L4.3213.9 GB90%
IQ4_XS4.46221.8 GB92%
Q4_K_S4.67232.2 GB93%
Q4_K_M4.89243.2 GB94%
Q5_K_S5.57276.9 GB96%
Q5_K_M5.7283.4 GB96%
Q6_K6.56326.0 GB97%
Q8_08.5422.3 GB100%
FP1616794.5 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO87.8
IFEval92.6
LiveCodeBench83.6
SWE-bench76.4
AIME91.3
GPQA Diamond88.4
HLE28.7
AA Intelligence45.0
AA Coding41.3
aa_ifbench78.8
aa_terminal_bench40.9
aa_tau295.6
aa_scicode42.0
aa_lcr65.7
§ 02RUN COMMAND

Run Qwen3.5-397B-A17B locally with Ollama — needs 243.2 GB VRAM at Q4_K_M:

$ollama run qwen3.5:397b-a17b
§ 03COMPATIBLE GPUs
5 @ Q4_K_M
AMD Radeon Instinct MI325X
288 GB · 10300 GB/s
AMD Radeon Instinct MI350X
288 GB · 8190 GB/s
AMD Radeon Instinct MI355X
288 GB · 8190 GB/s
Apple M4 Ultra (384GB)
384 GB · 1092 GB/s
Apple M5 Ultra (384GB)
384 GB · 1228 GB/s