GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 22, 2026 · Apple M2 Max
Global Score
66 vs 95
Hardware Fit
14 vs 94
Quality Score
88 vs 96
Hardware
GPT-120B:120b qwen3-30b-a3b-thin…
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 qwen3-30b-a3b-thin…
Tokens/sec10.180.4
First chunk6562 ms46 ms
TTFT10.3 s1.8 s
Load time49.8 sN/A
Memory usage61.5 GB21.2 GB
Memory %96%22%
HW Fit Score Breakdown
GPT-120B:120b
Speed
10/50
TTFT
2/20
Memory
2/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
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
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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