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

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
72 vs 66
Hardware Fit
35 vs 91
Quality Score
88 vs 55

Hardware

qwen/qwen3.5-35b-a3b qwen3.8-27b-mlx
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M5 Max
Cores1618
RAM32 GB64 GB
GPUAMD Radeon RX 9060 XTApple M5 Max
OSMicrosoft Windows 11 Home 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.5-35b-a3b qwen3.8-27b-mlx
Tokens/sec8.333.2
First chunk32 ms7 ms
TTFT2.0 s311 ms
Load timeN/AN/A
Memory usage28.9 GB0.5 GB
Memory %91%1%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

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

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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