Back to leaderboard

glm-4.7-flash:q4_K_M

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

Global Score
81 vs 70
Hardware Fit
89 vs 93
Quality Score
77 vs 60

Hardware

glm-4.7-flash:q4_K_M qwen3.5-2b-mlx
MachineASUSMacBook Air
CPUIntel Core™ i5-14600KFApple M4
Cores2010
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M4
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

glm-4.7-flash:q4_K_M qwen3.5-2b-mlx
Tokens/sec35.132.9
First chunk440 ms3096 ms
TTFT440 ms3.1 s
Load time11.6 sN/A
Memory usage18.4 GB2.5 GB
Memory %58%8%

HW Fit Score Breakdown

glm-4.7-flash:q4_K_M

Speed
49/50
TTFT
20/20
Memory
20/30

qwen3.5-2b-mlx

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

Quality

glm-4.7-flash:q4_K_M

Reasoning
13/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5-2b-mlx

Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View glm-4.7-flash:q4_K_M details | View qwen3.5-2b-mlx 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