Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Xeon® E5-2637 v3

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
49 vs 74
Hardware Fit
54 vs 99
Quality Score
47 vs 63

Hardware

qwen3.5:35b-a3b-q4… llama3.2:3b
MachineDell Inc. Precision Tower 7910NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Xeon® E5-2637 v3Cortex-A78AE
Cores166
RAM96 GB7 GB
GPUNVIDIA GeForce RTX 5060 TiIntegrated / Unknown
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… llama3.2:3b
Tokens/sec21.621.1
First chunk1505 ms1032 ms
TTFT30.0 s1.0 s
Load time53.8 s8.4 s
Memory usage22.7 GB2.4 GB
Memory %24%32%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
24/50
TTFT
0/20
Memory
30/30

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
5/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

llama3.2:3b

Reasoning
10/20
Coding
14/20
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

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