Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

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

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Xeon® E5-4620 0

Global Score
83 vs 10
Hardware Fit
100 vs 33
Quality Score
76 vs 0

Hardware

qwen3.5:4b qwen3.5-35b-a3b-t4…
MachineMacBook ProDell Inc. PowerEdge R820
CPUApple M1 MaxIntel Xeon® E5-4620 0
Cores1064
RAM32 GB256 GB
GPUApple M1 MaxMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 26.3Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:4b qwen3.5-35b-a3b-t4…
Tokens/sec32.43.5
First chunk306 ms3509 ms
TTFT306 ms30.0 s
Load time2.7 s30.0 s
Memory usage6.5 GB22.0 GB
Memory %20%9%

HW Fit Score Breakdown

qwen3.5:4b

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

qwen3.5-35b-a3b-t48-c8k…

Speed
3/50
TTFT
0/20
Memory
30/30

Quality

qwen3.5:4b

Reasoning
16/20
Coding
14/20
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

qwen3.5-35b-a3b-t48-c8k…

Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3.5:4b details | View qwen3.5-35b-a3b-t4… 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