Back to leaderboard

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

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
20 vs 68
Hardware Fit
37 vs 59
Quality Score
12 vs 72

Hardware

qwen3.5:27b 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

qwen3.5:27b qwen2.5-coder:7b
Tokens/sec10.634.4
First chunk358 ms1991 ms
TTFT13.7 s2.0 s
Load time10.8 s40.6 s
Memory usage39.7 GB5.0 GB
Memory %32%8%

HW Fit Score Breakdown

qwen3.5:27b

Speed
9/50
TTFT
0/20
Memory
28/30

qwen2.5-coder:7b

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

Quality

qwen3.5:27b

Reasoning
2/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
8/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor 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