Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 7, 2026 · AMD Ryzen 5 5500

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

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

Global Score
71 vs 68
Hardware Fit
56 vs 59
Quality Score
78 vs 72

Hardware

qwen3.5:9b qwen2.5-coder:7b
MachineSystem manufacturerASUS
CPUAMD Ryzen 5 5500Intel Gen Intel® Core™ i7-13700K
Cores1224
RAM16 GB64 GB
GPUNVIDIA GeForce RTX 3060NVIDIA GeForce RTX 3070
OSMicrosoft Windows 11 IoT Enterprise LTSC 10.0.26100Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedunknown

Performance

qwen3.5:9b qwen2.5-coder:7b
Tokens/sec5.334.4
First chunk1624 ms1991 ms
TTFT1.6 s2.0 s
Load time4.0 s40.6 s
Memory usage7.9 GB5.0 GB
Memory %50%8%

HW Fit Score Breakdown

qwen3.5:9b

Speed
11/50
TTFT
20/20
Memory
25/30

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

Quality

qwen3.5:9b

Reasoning
14/20
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

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:9b details | View qwen2.5-coder:7b 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