Back to leaderboard

qwen3.5:9b-q8_0

OLLAMA GGUF

qwen35 · 9.7B · Q8_0

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Global Score
86 vs 73
Hardware Fit
100 vs 64
Quality Score
80 vs 77

Hardware

qwen3.5:9b-q8_0 mistralai/devstral…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4MacBook Pro
CPUIntel Core™ i5-14400FApple M1 Pro
Cores1610
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 5060 TiApple M1 Pro
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:9b-q8_0 mistralai/devstral…
Tokens/sec37.711.9
First chunk120 ms7 ms
TTFT120 ms1.1 s
Load time8.3 sN/A
Memory usage8.4 GB19.7 GB
Memory %26%62%

HW Fit Score Breakdown

qwen3.5:9b-q8_0

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

mistralai/devstral-smal…

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

Quality

qwen3.5:9b-q8_0

Reasoning
14/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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
View qwen3.5:9b-q8_0 details | View mistralai/devstral… 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