Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

qwen2.5-coder:14b

OLLAMA GGUF

qwen2 · 14.8B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
82 vs 86
Hardware Fit
81 vs 100
Quality Score
82 vs 80

Hardware

qwen3.5:9b qwen2.5-coder:14b
MachineAZW GTR ProGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SIntel Core™ i5-14400F
Cores3216
RAM125 GB32 GB
GPUIntegrated / Apple SiliconNVIDIA GeForce RTX 5060 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5:9b qwen2.5-coder:14b
Tokens/sec30.838.3
First chunk195 ms78 ms
TTFT195 ms78 ms
Load time6.8 s6.3 s
Memory usage18.8 GB8.8 GB
Memory %15%28%

HW Fit Score Breakdown

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

qwen2.5-coder:14b

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

Quality

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen2.5-coder:14b

Reasoning
14/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:9b details | View qwen2.5-coder:14b 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