Back to leaderboard

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

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Sep 6, 2026 · Intel Xeon® E5-4650 v2

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jun 5, 2026 · AMD Ryzen 7 5800H

Global Score
81 vs 89
Hardware Fit
63 vs 83
Quality Score
88 vs 92

Hardware

qwen3.5-35b-a3b-t4… gemma4:latest
MachineDell Inc. PowerEdge R820LENOVO 82JQ
CPUIntel Xeon® E5-4650 v2AMD Ryzen 7 5800H
Cores8016
RAM256 GB16 GB
GPUMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display AdapterNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5-35b-a3b-t4… gemma4:latest
Tokens/sec17.246.3
First chunk845 ms824 ms
TTFT845 ms3.8 s
Load time103.1 s21.0 s
Memory usage21.9 GB8.9 GB
Memory %9%56%

HW Fit Score Breakdown

qwen3.5-35b-a3b-t48-c8k…

Speed
16/50
TTFT
17/20
Memory
30/30

gemma4:latest

Speed
50/50
TTFT
11/20
Memory
22/30

Quality

qwen3.5-35b-a3b-t48-c8k…

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma4:latest

Reasoning
18/20
Coding
19/20
Instruction
15/20
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest