Back to leaderboard

mistral-small:24b

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
75 vs 82
Hardware Fit
64 vs 88
Quality Score
80 vs 80

Hardware

mistral-small:24b unsloth-phi-4
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB64 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archarm64arm64
Power Modeperformancebalanced

Performance

mistral-small:24b unsloth-phi-4
Tokens/sec14.327.4
First chunk327 ms457 ms
TTFT327 ms457 ms
Load time12.0 sN/A
Memory usage18.5 GB7.7 GB
Memory %15%12%

HW Fit Score Breakdown

mistral-small:24b

Speed
14/50
TTFT
20/20
Memory
30/30

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

Quality

mistral-small:24b

Reasoning
16/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View mistral-small:24b details | View unsloth-phi-4 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