Back to leaderboard

glm-4.6v-flash

LM-STUDIO GGUF

glm4 · Q4_K_S

Good

Apr 21, 2026 · Apple M2 Max

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 22, 2026 · Apple M1 Pro

Global Score
65 vs 69
Hardware Fit
88 vs 85
Quality Score
55 vs 62

Hardware

glm-4.6v-flash qwen3.5:4b
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M1 Pro
Cores1210
RAM96 GB16 GB
GPUApple M2 MaxApple M1 Pro
OSmacOS 26.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

glm-4.6v-flash qwen3.5:4b
Tokens/sec49.936.9
First chunk27 ms474 ms
TTFT3.7 s6.9 s
Load time2.7 s2.9 s
Memory usage0.0 GB5.3 GB
Memory %0%33%

HW Fit Score Breakdown

glm-4.6v-flash

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

qwen3.5:4b

Speed
50/50
TTFT
6/20
Memory
29/30

Quality

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

qwen3.5:4b

Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong
View glm-4.6v-flash details | View qwen3.5:4b 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