Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

glm-4.7-flash:q4_K_M

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
57 vs 81
Hardware Fit
61 vs 89
Quality Score
55 vs 77

Hardware

qwen3.5:9b glm-4.7-flash:q4_K_M
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-14600KF
Cores3220
RAM125 GB32 GB
GPUAMD Radeon 8060SNVIDIA GeForce RTX 4070 Ti SUPER
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:9b glm-4.7-flash:q4_K_M
Tokens/sec30.335.1
First chunk205 ms440 ms
TTFT8.7 s440 ms
Load time5.6 s11.6 s
Memory usage18.8 GB18.4 GB
Memory %15%58%

HW Fit Score Breakdown

qwen3.5:9b

Speed
30/50
TTFT
1/20
Memory
30/30

glm-4.7-flash:q4_K_M

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

Quality

qwen3.5:9b

Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

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
View qwen3.5:9b details | View glm-4.7-flash:q4_K_M 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