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

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

Global Score
62 vs 35
Hardware Fit
100 vs 45
Quality Score
46 vs 30

Hardware

qwen3-vl-4b-instru… qwen3.5:35b-a3b-q4…
MachineMac StudioMicro-Star International Co., Ltd. MS-7D98
CPUApple M2 MaxIntel Core™ i9-14900K
Cores1232
RAM96 GB128 GB
GPUApple M2 MaxIntel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-vl-4b-instru… qwen3.5:35b-a3b-q4…
Tokens/sec67.216.7
First chunk66 ms781 ms
TTFT68 ms30.0 s
Load time0.0 s19.9 s
Memory usage0.2 GB21.8 GB
Memory %0%17%

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
15/50
TTFT
0/20
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
8/20
Coding
0/20
Instruction
4/20
Structured
3/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak 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