Back to leaderboard

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 10, 2026 · Apple M4

Global Score
72 vs 66
Hardware Fit
35 vs 34
Quality Score
88 vs 80

Hardware

qwen/qwen3.5-35b-a3b qwen3.5:27b
MachineSystem manufacturerMac mini
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M4
Cores1610
RAM32 GB24 GB
GPUAMD Radeon RX 9060 XTApple M4
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.5-35b-a3b qwen3.5:27b
Tokens/sec8.34.0
First chunk32 ms1655 ms
TTFT2.0 s1.7 s
Load timeN/A12.9 s
Memory usage28.9 GB21.3 GB
Memory %91%89%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

qwen3.5:27b

Speed
8/50
TTFT
20/20
Memory
6/30

Quality

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:27b

Reasoning
16/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.5-35b-a3b details | View qwen3.5:27b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest