Qwen3.5 122B-A10B Instruct

Qwen3.5 122B-A10B Instruct loads in 72 GB at Q4_K_M and is comfortable from 96 GB of memory, Macs included from the MacBook Pro M5 Max 128GB. Below: the full memory math, the cheapest card that runs it well, and the fastest machine we track.

PARAMETERS
122B (10B active)
FORMAT
Q4_K_M
MIN MEMORY
96 GB
BEST FOR
Frontier-level reasoning, Complex tasks

Memory math

Weights (Q4_K_M)
72 GB
+ KV cache (16k)
~0.4 GB
Total at 16k
~72.4 GB
Comfortable from
96 GB

KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).

Hardware snapshot

Cheapest GPU
~9 tok/s est. — ~$3,847 used (as of 2026-07-31)
Fastest
~41 tok/s est.
Runs on a Mac?
~19 tok/s est.

More Qwen models

Qwen3.7-PlusQwen2.5 0.5B InstructQwen3.5 0.8B InstructQwen2.5 1.5B InstructQwen3.5 2B InstructQwen2.5 3B InstructQwen3.5 4B InstructQwen2.5 7B InstructQwen2.5 Coder 7BQwen3 8BQwen3.5 9B InstructQwen2.5 14B InstructQwen2.5 Coder 14BQwen3 14BQwen3.5 27B InstructQwen3.6 27BQwen3.8 27BQwen3 30BQwen3 30B (Q8)Qwen3.5 35B-A3B InstructQwen3.6 35B-A3BQwen3-Next 80B-A3BQwen3.8-Flash-NextQwen3 235B A22B

Frequently asked questions

How much memory does Qwen3.5 122B-A10B Instruct need?

72 GB for the Q4_K_M weights, plus ~0.4 GB of KV-cache at 16k context — about 72.4 GB total. Comfortable from 96 GB of VRAM or unified memory.

Does Qwen3.5 122B-A10B Instruct run on a Mac?

Yes — from the MacBook Pro M5 Max 128GB (~19 tok/s est.). Unified memory means the RAM budget is the only limit.

What is the cheapest GPU for Qwen3.5 122B-A10B Instruct?

The AMD Ryzen AI Max+ 395 (Strix Halo) is the cheapest tracked card that runs Qwen3.5 122B-A10B Instruct comfortably — ~9 tok/s est. at ~$3,847 used (as of 2026-07-31).

Cite this page

ModelFit: Qwen3.5 122B-A10B Instruct — specs, memory math and hardware verdicts.
https://modelfit.io/models/qwen3.5-122b-a10b/ (dataset updated 2026-09-03, CC BY 4.0).