Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

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

Global Score
57 vs 68
Hardware Fit
61 vs 59
Quality Score
55 vs 72

Hardware

qwen3.5:9b qwen2.5-coder:7b
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i7-13700K
Cores3224
RAM125 GB64 GB
GPUAMD Radeon 8060SNVIDIA GeForce RTX 3070
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerunknown

Performance

qwen3.5:9b qwen2.5-coder:7b
Tokens/sec30.334.4
First chunk205 ms1991 ms
TTFT8.7 s2.0 s
Load time5.6 s40.6 s
Memory usage18.8 GB5.0 GB
Memory %15%8%

HW Fit Score Breakdown

qwen3.5:9b

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

qwen2.5-coder:7b

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

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

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

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