huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor
smollm2-360m-instruct
LM-STUDIO GGUFllama · 360M · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
88 vs 48
Hardware Fit
94 vs 98
Quality Score
85 vs 26
Hardware
huihui-qwen3.6-35b… smollm2-360m-instr…
MachineGigabyte Technology Co., Ltd. B550M AORUS PROLENOVO 20BUS00700
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Core™ i5-5300U
Cores124
RAM47 GB16 GB
GPUAD106 [GeForce RTX 4060 Ti]Intel(R) HD Graphics 5500
OScachyos rollingMicrosoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modelow-powerbalanced
Performance
huihui-qwen3.6-35b… smollm2-360m-instr…
Tokens/sec39.820.0
First chunk3 ms1116 ms
TTFT479 ms1.1 s
Load timeN/AN/A
Memory usage24.4 GB0.3 GB
Memory %52%2%
HW Fit Score Breakdown
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
20/20
Memory
24/30
smollm2-360m-instruct
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
huihui-qwen3.6-35b-a3b-…
Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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