Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Jul 31, 2026 · Intel Core™ i9-14900K

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Marginal

Jun 26, 2026 · Cortex-A78AE

Global Score
79 vs 46
Hardware Fit
62 vs 61
Quality Score
86 vs 40

Hardware

qwen3.5:35b-a3b-q4… llama3.1:8b
MachineMicro-Star International Co., Ltd. MS-7D98NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i9-14900KCortex-A78AE
Cores326
RAM128 GB7 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Integrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… llama3.1:8b
Tokens/sec16.47.8
First chunk787 ms1625 ms
TTFT787 ms1.6 s
Load time19.3 s21.8 s
Memory usage21.8 GB5.2 GB
Memory %17%71%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
17/20
Memory
30/30

llama3.1:8b

Speed
26/50
TTFT
20/20
Memory
15/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
17/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

llama3.1:8b

Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor 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