Back to leaderboard

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 18, 2026 · Intel Core™ i7-14700F

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score
66 vs 78
Hardware Fit
14 vs 51
Quality Score
88 vs 89

Hardware

GPT-120B:120b qwen3.5-35b-a3b-t4…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCDell Inc. PowerEdge R820
CPUIntel Core™ i7-14700FIntel Xeon® E5-4650 v2
Cores2880
RAM64 GB256 GB
GPUNVIDIA GeForce RTX 5080Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

GPT-120B:120b qwen3.5-35b-a3b-t4…
Tokens/sec10.17.1
First chunk6562 ms997 ms
TTFT10.3 s997 ms
Load time49.8 s45.4 s
Memory usage61.5 GB21.6 GB
Memory %96%8%

HW Fit Score Breakdown

GPT-120B:120b

Speed
10/50
TTFT
2/20
Memory
2/30

qwen3.5-35b-a3b-t48-c8k…

Speed
6/50
TTFT
15/20
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

qwen3.5-35b-a3b-t48-c8k…

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest