GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_S
Apr 20, 2026 · Apple M2 Max
Global Score
66 vs 82
Hardware Fit
14 vs 80
Quality Score
88 vs 83
Hardware
GPT-120B:120b qwen3.6-35b-a3b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMac Studio
CPUIntel Core™ i7-14700FApple M2 Max
Cores2812
RAM64 GB96 GB
GPUNVIDIA GeForce RTX 5080Apple M2 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3.6-35b-a3b
Tokens/sec10.154.7
First chunk6562 ms32 ms
TTFT10.3 s30.0 s
Load time49.8 sN/A
Memory usage61.5 GB30.3 GB
Memory %96%32%
HW Fit Score Breakdown
GPT-120B:120b
Speed
10/50
TTFT
2/20
Memory
2/30
qwen3.6-35b-a3b
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
GPT-120B:120b
Reasoning
18/20
Coding
19/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.6-35b-a3b
Reasoning
18/20
Coding
10/20
Instruction
18/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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