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

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

Global Score
49 vs 81
Hardware Fit
54 vs 98
Quality Score
47 vs 74

Hardware

qwen3.5:35b-a3b-q4… qwen3.5:4b
MachineDell Inc. Precision Tower 7910Microsoft WSL
CPUIntel Xeon® E5-2637 v3AMD Ryzen 5 5500
Cores1612
RAM96 GB8 GB
GPUNVIDIA GeForce RTX 5060 TiIntegrated / Unknown
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedunknown

Performance

qwen3.5:35b-a3b-q4… qwen3.5:4b
Tokens/sec21.693.7
First chunk1505 ms249 ms
TTFT30.0 s249 ms
Load time53.8 s10.1 s
Memory usage22.7 GB2.9 GB
Memory %24%38%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

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

qwen3.5:4b

Speed
50/50
TTFT
20/20
Memory
28/30

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

qwen3.5:4b

Reasoning
15/20
Coding
13/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:35b-a3b-q4… details | View qwen3.5:4b details

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