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

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
65 vs 62
Hardware Fit
29 vs 99
Quality Score
81 vs 46

Hardware

qwen3-235b-a22b-t4… microsoft/phi-4-mi…
MachineDell Inc. PowerEdge R820MacBook Air
CPUIntel Xeon® E5-4650 v2Apple M4
Cores8010
RAM256 GB32 GB
GPUMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display AdapterApple M4
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-235b-a22b-t4… microsoft/phi-4-mi…
Tokens/sec2.440.3
First chunk5833 ms289 ms
TTFT5.8 s289 ms
Load time0.0 sN/A
Memory usage135.1 GB2.0 GB
Memory %53%6%

HW Fit Score Breakdown

qwen3-235b-a22b-t48-c8k…

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

microsoft/phi-4-mini-re…

Speed
50/50
TTFT
20/20
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

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate

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