Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

glm-4.6v-flash

LM-STUDIO GGUF

glm4 · Q4_K_S

Good

Apr 21, 2026 · Apple M2 Max

Global Score
89 vs 65
Hardware Fit
97 vs 88
Quality Score
86 vs 55

Hardware

qwen/qwen3.6-35b-a3b glm-4.6v-flash
MachineMacBook ProMac Studio
CPUApple M5 MaxApple M2 Max
Cores1812
RAM64 GB96 GB
GPUApple M5 MaxApple M2 Max
OSmacOS 27.0macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.6-35b-a3b glm-4.6v-flash
Tokens/sec130.249.9
First chunk5 ms27 ms
TTFT135 ms3.7 s
Load timeN/A2.7 s
Memory usage26.6 GB0.0 GB
Memory %42%0%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
27/30

glm-4.6v-flash

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

Quality

qwen/qwen3.6-35b-a3b

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

glm-4.6v-flash

Reasoning
0/20
Coding
16/20
Instruction
12/20
Structured
2/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Strong Instruction Following: Adequate Structured Output: Poor Math: Strong Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View glm-4.6v-flash 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