FitMyLLM
Alibaba/Mixture of Experts

AlibabaQwen 3.5 122B A10B

Qwen 3.5 122B A10B — MoE multimodal flagship. 256 experts, 10B active. Near-frontier on coding, reasoning, and vision.

chatcodingreasoningmultilingualvisionmath
122B
Parameters (10B active)
256K
Context length
21
Benchmarks
17
Quantizations
621K
HF downloads
Architecture
MoE
Released
2026-02-24
Layers
48
KV Heads
2
Head Dim
256
Family
qwen

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
IQ2_XXS2.38
37.1 GB
36.8 + 0.3 KV
low
IQ2_M2.93
45.5 GB
45.2 + 0.3 KV
low
Q2_K3.16
49.0 GB
48.7 + 0.3 KV
low
IQ3_XXS3.25
50.3 GB
50.1 + 0.3 KV
low
IQ3_XS3.5
54.1 GB
53.9 + 0.3 KV
low
Q3_K_S3.64
56.3 GB
56.0 + 0.3 KV
low
IQ3_M3.76
58.1 GB
57.8 + 0.3 KV
low
Q3_K_M4
61.8 GB
61.5 + 0.3 KV
low
Q3_K_L4.3
66.3 GB
66.1 + 0.3 KV
moderate
IQ4_XS4.46
68.8 GB
68.5 + 0.3 KV
moderate
Q4_K_S4.67
72.0 GB
71.7 + 0.3 KV
moderate
Q4_K_M4.89
75.3 GB
75.1 + 0.3 KV
good
Q5_K_S5.57
85.7 GB
85.4 + 0.3 KV
good
Q5_K_M5.7
87.7 GB
87.4 + 0.3 KV
good
Q6_K6.56
100.8 GB
100.5 + 0.3 KV
excellent
Q8_08.5
130.4 GB
130.1 + 0.3 KV
lossless
FP1616
244.8 GB
244.5 + 0.3 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 122B A10B 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 (21)

Arena Elo1492
τ²-Bench93.6
IFEval93.4
MMBench92.8
MMLU-PRO86.7
GPQA Diamond86.6
MMMU83.9
LiveCodeBench78.9
IFBench75.7
SWE-bench72.0
AA Long Context66.7
BBH45.0
SciCode42.0
AA Intelligence41.6
BigCodeBench35.0
AA Coding34.7
Terminal-Bench31.1
HLE25.3
MATH23.4
MUSR16.3
GPQA12.2

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run qwen3.5:122b-a10b-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 H100 SXM5 80GB
80 GB VRAM • 3350 GB/s
NVIDIA
$25000
NVIDIA H100 PCIe 80GB
80 GB VRAM • 2000 GB/s
NVIDIA
$25000
NVIDIA A100 SXM 80GB
80 GB VRAM • 2039 GB/s
NVIDIA
$10000
NVIDIA A100 PCIe 80GB
80 GB VRAM • 1935 GB/s
NVIDIA
$10000
NVIDIA A100 SXM4 80 GB
80 GB VRAM • 2040 GB/s
NVIDIA
$15000
NVIDIA A100 PCIe 80 GB
80 GB VRAM • 1940 GB/s
NVIDIA
$10000
NVIDIA A100X
80 GB VRAM • 2040 GB/s
NVIDIA
NVIDIA H100 PCIe 80 GB
80 GB VRAM • 2040 GB/s
NVIDIA
$25000
NVIDIA H100 SXM5 80 GB
80 GB VRAM • 3360 GB/s
NVIDIA
$25000
NVIDIA H100 CNX
80 GB VRAM • 2040 GB/s
NVIDIA
$25000
NVIDIA A800 PCIe 80 GB
80 GB VRAM • 1940 GB/s
NVIDIA
NVIDIA A800 SXM4 80 GB
80 GB VRAM • 2040 GB/s
NVIDIA
NVIDIA H800 PCIe 80 GB
80 GB VRAM • 2040 GB/s
NVIDIA
NVIDIA H800 SXM5
80 GB VRAM • 3360 GB/s
NVIDIA
NVIDIA RTX 6000D
84 GB VRAM • 1570 GB/s
NVIDIA
$7500
NVIDIA B200
90 GB VRAM • 4100 GB/s
NVIDIA
$30000
NVIDIA H100 NVL 94 GB
94 GB VRAM • 3940 GB/s
NVIDIA
$30000
NVIDIA H100 SXM5 94 GB
94 GB VRAM • 3360 GB/s
NVIDIA
$25000
RTX Pro 6000
96 GB VRAM • 1792 GB/s
NVIDIA
$8565
NVIDIA H100 PCIe 96 GB
96 GB VRAM • 3360 GB/s
NVIDIA
$25000
NVIDIA H100 SXM5 96 GB
96 GB VRAM • 3360 GB/s
NVIDIA
$25000
Intel Data Center GPU Max 1350
96 GB VRAM • 2460 GB/s
INTEL
NVIDIA RTX PRO 6000 Blackwell Server
96 GB VRAM • 1790 GB/s
NVIDIA
$9999
NVIDIA RTX PRO 6000 Blackwell
96 GB VRAM • 1790 GB/s
NVIDIA
$9999
AMD Instinct MI300A
120 GB VRAM • 5300 GB/s
AMD
$12000
Apple M4 Max (128GB)
128 GB VRAM • 546 GB/s
APPLE
$3999
AMD Instinct MI250X
128 GB VRAM • 3277 GB/s
AMD
$10000
Apple M1 Ultra (128GB)
128 GB VRAM • 800 GB/s
APPLE
$4999
Apple M2 Ultra (128GB)
128 GB VRAM • 800 GB/s
APPLE
$3999
AMD Radeon Instinct MI250
128 GB VRAM • 3280 GB/s
AMD
$12000

Find the best GPU for Qwen 3.5 122B A10B

Build Hardware for Qwen 3.5 122B A10B
▸ SPEC SHEET

Qwen 3.5 122B A10B — 122B MoE.

▸ SPECIFICATIONS
PARAMETERS
122B (10B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
256K tokens
CAPABILITIES
chat, coding, reasoning, multilingual, vision, math
RELEASE DATE
2026-02-24
PROVIDER
Alibaba
FAMILY
qwen
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ2_XXS2.3836.8 GB65%
IQ2_M2.9345.2 GB75%
Q2_K3.1648.7 GB78%
IQ3_XXS3.2550.1 GB82%
IQ3_XS3.553.9 GB84%
Q3_K_S3.6456.0 GB85%
IQ3_M3.7657.8 GB86%
Q3_K_M461.5 GB88%
Q3_K_L4.366.1 GB90%
IQ4_XS4.4668.5 GB92%
Q4_K_S4.6771.7 GB93%
Q4_K_M4.8975.1 GB94%
Q5_K_S5.5785.4 GB96%
Q5_K_M5.787.4 GB96%
Q6_K6.56100.5 GB97%
Q8_08.5130.1 GB100%
FP1616244.5 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO86.7
MATH23.4
IFEval93.4
BBH45.0
MMMU83.9
GPQA12.2
MUSR16.3
BigCodeBench35.0
MMBench92.8
Arena Elo1492.0
GPQA Diamond86.6
HLE25.3
AA Intelligence41.6
AA Coding34.7
LiveCodeBench78.9
SWE-bench72.0
aa_ifbench75.7
aa_terminal_bench31.1
aa_tau293.6
aa_scicode42.0
aa_lcr66.7
§ 02RUN COMMAND

Run Qwen 3.5 122B A10B locally with Ollama — needs 75.1 GB VRAM at Q4_K_M:

$ollama run qwen3.5:122b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA H100 SXM5 80GB
80 GB · 3350 GB/s
NVIDIA H100 PCIe 80GB
80 GB · 2000 GB/s
NVIDIA A100 SXM 80GB
80 GB · 2039 GB/s
NVIDIA A100 PCIe 80GB
80 GB · 1935 GB/s
NVIDIA A100 SXM4 80 GB
80 GB · 2040 GB/s
NVIDIA A100 PCIe 80 GB
80 GB · 1940 GB/s
NVIDIA A100X
80 GB · 2040 GB/s
NVIDIA H100 PCIe 80 GB
80 GB · 2040 GB/s
NVIDIA H100 SXM5 80 GB
80 GB · 3360 GB/s
NVIDIA H100 CNX
80 GB · 2040 GB/s
NVIDIA A800 PCIe 80 GB
80 GB · 1940 GB/s
NVIDIA A800 SXM4 80 GB
80 GB · 2040 GB/s
NVIDIA H800 PCIe 80 GB
80 GB · 2040 GB/s
NVIDIA H800 SXM5
80 GB · 3360 GB/s
NVIDIA RTX 6000D
84 GB · 1570 GB/s