Back to leaderboard

qwen3-235b-a22b-t48-c8k:latest

OLLAMA GGUF

qwen3moe · 235.1B · Q4_K_M

Not Rec.

Sep 7, 2026 · Intel Xeon® E5-4650 v2

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
65 vs 62
Hardware Fit
29 vs 35
Quality Score
81 vs 73

Hardware

qwen3-235b-a22b-t4… qwen3.5-4b-mlx
MachineDell Inc. PowerEdge R820Mac mini
CPUIntel Xeon® E5-4650 v2Apple M4 Pro
Cores8014
RAM256 GB64 GB
GPUMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display AdapterApple M4 Pro
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-235b-a22b-t4… qwen3.5-4b-mlx
Tokens/sec2.40.0
First chunk5833 ms5548 ms
TTFT5.8 s5.5 s
Load time0.0 sN/A
Memory usage135.1 GB2.9 GB
Memory %53%5%

HW Fit Score Breakdown

qwen3-235b-a22b-t48-c8k…

Speed
2/50
TTFT
3/20
Memory
24/30

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

Quality

qwen3-235b-a22b-t48-c8k…

Reasoning
19/20
Coding
15/20
Instruction
10/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong 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