Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

vlm · 7.9B · Q4_K_M

Marginal

Oct 1, 2026 · AMD Ryzen 7 4800H

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Global Score
59 vs 73
Hardware Fit
62 vs 64
Quality Score
58 vs 77

Hardware

google/gemma-4-e4b mistralai/devstral…
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMMacBook Pro
CPUAMD Ryzen 7 4800HApple M1 Pro
Cores1610
RAM15 GB32 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b mistralai/devstral…
Tokens/sec7.111.9
First chunk41 ms7 ms
TTFT1.2 s1.1 s
Load time71.7 sN/A
Memory usage0.9 GB19.7 GB
Memory %6%62%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
12/50
TTFT
20/20
Memory
30/30

mistralai/devstral-smal…

Speed
25/50
TTFT
20/20
Memory
19/30

Quality

google/gemma-4-e4b

Reasoning
6/20
Coding
14/20
Instruction
12/20
Structured
15/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

mistralai/devstral-smal…

Reasoning
17/20
Coding
16/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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