Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

Global Score
35 vs 73
Hardware Fit
45 vs 100
Quality Score
30 vs 62

Hardware

qwen3.5:35b-a3b-q4… mistral:latest
MachineMicro-Star International Co., Ltd. MS-7D98Micro-Star International Co., Ltd. MS-7B79
CPUIntel Core™ i9-14900KAMD Ryzen 5 2600X Six-Core Processor
Cores3212
RAM128 GB16 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000NVIDIA GeForce GTX 1080
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… mistral:latest
Tokens/sec16.731.7
First chunk781 ms102 ms
TTFT30.0 s102 ms
Load time19.9 s14.3 s
Memory usage21.8 GB4.8 GB
Memory %17%30%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
0/20
Memory
30/30

mistral:latest

Speed
50/50
TTFT
20/20
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

mistral:latest

Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:35b-a3b-q4… details | View mistral:latest 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