Back to leaderboard

llama3.2:latest

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

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

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 1, 2026 · Intel Xeon® E5-4620 0

Global Score
76 vs 65
Hardware Fit
100 vs 38
Quality Score
65 vs 76

Hardware

llama3.2:latest qwen3.5-35b-a3b-t4…
MachineMicro-Star International Co., Ltd. MS-7B79Dell Inc. PowerEdge R820
CPUAMD Ryzen 5 2600X Six-Core ProcessorIntel Xeon® E5-4620 0
Cores1264
RAM16 GB256 GB
GPUNVIDIA GeForce GTX 1080Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

llama3.2:latest qwen3.5-35b-a3b-t4…
Tokens/sec57.03.4
First chunk264 ms4210 ms
TTFT264 ms4.2 s
Load time9.7 s45.1 s
Memory usage2.6 GB22.0 GB
Memory %16%9%

HW Fit Score Breakdown

llama3.2:latest

Speed
50/50
TTFT
20/20
Memory
30/30

qwen3.5-35b-a3b-t48-c8k…

Speed
3/50
TTFT
5/20
Memory
30/30

Quality

llama3.2:latest

Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

qwen3.5-35b-a3b-t48-c8k…

Reasoning
16/20
Coding
15/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Adequate 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