Back to leaderboard

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

stablelm-2-zephyr-1.6b

LM-STUDIO GGUF

stablelm · 1.6B · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
20 vs 35
Hardware Fit
37 vs 61
Quality Score
12 vs 24

Hardware

qwen3.5:27b stablelm-2-zephyr-…
MachineAZW GTR ProLENOVO 20BUS00700
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-5300U
Cores324
RAM125 GB16 GB
GPUAMD Radeon 8060SIntel(R) HD Graphics 5500
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:27b stablelm-2-zephyr-…
Tokens/sec10.66.5
First chunk358 ms3080 ms
TTFT13.7 s3.1 s
Load time10.8 sN/A
Memory usage39.7 GB1.0 GB
Memory %32%6%

HW Fit Score Breakdown

qwen3.5:27b

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

stablelm-2-zephyr-1.6b

Speed
23/50
TTFT
16/20
Memory
22/30

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

stablelm-2-zephyr-1.6b

Reasoning
2/20
Coding
2/20
Instruction
8/20
Structured
6/15
Math
2/15
Multilingual
4/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
View qwen3.5:27b details | View stablelm-2-zephyr-… 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