Back to leaderboard

mistralai/ministral-3-3b

LM-STUDIO GGUF

mistral3 · 3B · Q4_K_M

Good

Oct 31, 2026 · AMD RYZEN AI MAX+ 395

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
75 vs 83
Hardware Fit
90 vs 99
Quality Score
68 vs 76

Hardware

mistralai/ministra… qwen3.5:4b
MachineGMKtec EVO-X3MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM120 GB16 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

mistralai/ministra… qwen3.5:4b
Tokens/sec49.136.6
First chunk17 ms204 ms
TTFT677 ms204 ms
Load time7.7 s2.7 s
Memory usage48.1 GB5.3 GB
Memory %40%33%

HW Fit Score Breakdown

mistralai/ministral-3-3b

Speed
45/50
TTFT
18/20
Memory
27/30

qwen3.5:4b

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

Quality

mistralai/ministral-3-3b

Reasoning
10/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

qwen3.5:4b

Reasoning
16/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View mistralai/ministra… details | View qwen3.5:4b 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