Back to leaderboard

mistral-small:24b

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
75 vs 59
Hardware Fit
64 vs 63
Quality Score
80 vs 58

Hardware

mistral-small:24b qwen3.8-27b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M5 Max
Cores2018
RAM122 GB64 GB
GPUDevice 2e12Apple M5 Max
OSUbuntu 24.04.4 LTSmacOS 27.0
Archarm64arm64
Power Modeperformancebalanced

Performance

mistral-small:24b qwen3.8-27b-mlx
Tokens/sec14.318.3
First chunk327 ms4 ms
TTFT327 ms530 ms
Load time12.0 sN/A
Memory usage18.5 GB38.5 GB
Memory %15%60%

HW Fit Score Breakdown

mistral-small:24b

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

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
View mistral-small:24b details | View qwen3.8-27b-mlx 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