Back to leaderboard

qwen3-vl-4b-instruct-q4_k_m

OPENAI GGUF
Good

Apr 22, 2026 · Apple M2 Max

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Jul 31, 2026 · Intel Xeon® E5-2637 v3

Global Score
62 vs 81
Hardware Fit
100 vs 72
Quality Score
46 vs 85

Hardware

qwen3-vl-4b-instru… qwen3.5:35b-a3b-q4…
MachineMac StudioDell Inc. Precision Tower 7910
CPUApple M2 MaxIntel Xeon® E5-2637 v3
Cores1216
RAM96 GB96 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.1Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-vl-4b-instru… qwen3.5:35b-a3b-q4…
Tokens/sec67.224.2
First chunk66 ms1607 ms
TTFT68 ms1.6 s
Load time0.0 s66.4 s
Memory usage0.2 GB22.7 GB
Memory %0%24%

HW Fit Score Breakdown

qwen3-vl-4b-instruct-q4…

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

qwen3.5:35b-a3b-q4_K_M

Speed
28/50
TTFT
14/20
Memory
30/30

Quality

qwen3-vl-4b-instruct-q4…

Reasoning
16/20
Coding
0/20
Instruction
12/20
Structured
1/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Poor Math: Adequate Multilingual: Strong

qwen3.5:35b-a3b-q4_K_M

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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