Back to leaderboard

mlx-community/Llama-3.2-3B-Instruct-4bit

LM-STUDIO GGUF
Good

Mar 5, 2026 · Apple M4

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
74 vs 10
Hardware Fit
100 vs 33
Quality Score
63 vs 0

Hardware

mlx-community/Llam… qwen3.5-35b-a3b-t4…
MachineMacBook AirDell Inc. PowerEdge R820
CPUApple M4Intel Xeon® E5-4620 0
Cores1064
RAM32 GB256 GB
GPUApple M4Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 26.3Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

mlx-community/Llam… qwen3.5-35b-a3b-t4…
Tokens/sec50.63.5
First chunk257 ms3509 ms
TTFT257 ms30.0 s
Load timeN/A30.0 s
Memory usage0.7 GB22.0 GB
Memory %2%9%

HW Fit Score Breakdown

mlx-community/Llama-3.2…

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

mlx-community/Llama-3.2…

Reasoning
9/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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

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