Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

glm-4.7-flash-reap-39-i1

LM-STUDIO GGUF

deepseek2 · Q5_K_M

Excellent

Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
53 vs 80
Hardware Fit
72 vs 97
Quality Score
45 vs 73

Hardware

qwen3.5:9b glm-4.7-flash-reap…
MachineMacBook ProMicro-Star International Co., Ltd. MS-7E51
CPUApple M1 MaxAMD Ryzen 7 9700X 8-Core Processor
Cores1016
RAM32 GB31 GB
GPUApple M1 MaxNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:9b glm-4.7-flash-reap…
Tokens/sec18.6154.8
First chunk403 ms13 ms
TTFT10.2 s70 ms
Load time4.3 sN/A
Memory usage9.1 GB12.6 GB
Memory %28%41%

HW Fit Score Breakdown

qwen3.5:9b

Speed
38/50
TTFT
4/20
Memory
30/30

glm-4.7-flash-reap-39-i1

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

Quality

qwen3.5:9b

Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

glm-4.7-flash-reap-39-i1

Reasoning
13/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Adequate
View qwen3.5:9b details | View glm-4.7-flash-reap… 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