qwen3.6-27b-mtp
LM-STUDIO GGUFqwen35 · 27B · Q5_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
smollm2-360m-instruct
LM-STUDIO GGUFllama · 360M · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
89 vs 48
Hardware Fit
85 vs 98
Quality Score
91 vs 26
Hardware
qwen3.6-27b-mtp smollm2-360m-instr…
MachineASUSLENOVO 20BUS00700
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorIntel Core™ i5-5300U
Cores164
RAM31 GB16 GB
GPUNVIDIA GeForce RTX 4090, RaphaelIntel(R) HD Graphics 5500
OScachyos rollingMicrosoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modeperformancebalanced
Performance
qwen3.6-27b-mtp smollm2-360m-instr…
Tokens/sec74.920.0
First chunk3 ms1116 ms
TTFT235 ms1.1 s
Load timeN/AN/A
Memory usage21.5 GB0.3 GB
Memory %70%2%
HW Fit Score Breakdown
qwen3.6-27b-mtp
Speed
50/50
TTFT
20/20
Memory
15/30
smollm2-360m-instruct
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
qwen3.6-27b-mtp
Reasoning
18/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
smollm2-360m-instruct
Reasoning
3/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
3/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Weak
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest