Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 6bit

Excellent

Jul 17, 2026 · Apple M5 Max

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Not Rec.

Mar 22, 2026 · AMD RYZEN AI MAX+ 395

Global Score
87 vs 86
Hardware Fit
90 vs 74
Quality Score
86 vs 91

Hardware

qwen/qwen3.6-35b-a3b glm-4.7-flash:latest
MachineMacBook ProAZW GTR Pro
CPUApple M5 MaxAMD RYZEN AI MAX+ 395
Cores1832
RAM64 GB125 GB
GPUApple M5 MaxRadeon 8060S
OSmacOS 27.0Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen/qwen3.6-35b-a3b glm-4.7-flash:latest
Tokens/sec86.547.8
First chunk9 ms194 ms
TTFT175 ms30.0 s
Load timeN/A7.4 s
Memory usage37.9 GB37.7 GB
Memory %59%30%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

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

glm-4.7-flash:latest

Speed
44/50
TTFT
0/20
Memory
30/30

Quality

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

glm-4.7-flash:latest

Reasoning
19/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View glm-4.7-flash:latest 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