Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

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
77 vs 81
Hardware Fit
75 vs 89
Quality Score
78 vs 77

Hardware

qwen3.5:9b glm-4.7-flash:q4_K_M
MachineASUSASUS
CPUIntel Gen Intel® Core™ i7-13700KIntel Core™ i5-14600KF
Cores2420
RAM64 GB32 GB
GPUNVIDIA GeForce RTX 3070NVIDIA GeForce RTX 4070 Ti SUPER
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modeunknownbalanced

Performance

qwen3.5:9b glm-4.7-flash:q4_K_M
Tokens/sec30.535.1
First chunk291 ms440 ms
TTFT291 ms440 ms
Load time4.8 s11.6 s
Memory usage8.8 GB18.4 GB
Memory %14%58%

HW Fit Score Breakdown

qwen3.5:9b

Speed
34/50
TTFT
20/20
Memory
21/30

glm-4.7-flash:q4_K_M

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

Quality

qwen3.5:9b

Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate 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