qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score

35 vs 69

Hardware Fit

45 vs 50

Quality Score

30 vs 77

Hardware

qwen3.5:35b-a3b-q4… mistralai/devstral…

MachineMicro-Star International Co., Ltd. MS-7D98MacBook Air

CPUIntel Core™ i9-14900KApple M4

Cores3210

RAM128 GB32 GB

GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Apple M4

OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… mistralai/devstral…

Tokens/sec16.75.7

First chunk781 ms5007 ms

TTFT30.0 s5.0 s

Load time19.9 sN/A

Memory usage21.8 GB13.2 GB

Memory %17%41%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed

15/50

TTFT

0/20

Memory

30/30

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning

8/20

Coding

0/20

Instruction

4/20

Structured

3/15

Math

6/15

Multilingual

9/10

Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

View qwen3.5:35b-a3b-q4… 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