Back to leaderboard

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Sep 6, 2026 · Intel Xeon® E5-4650 v2

ornith-1.5-35b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Aug 21, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
81 vs 85
Hardware Fit
63 vs 88
Quality Score
88 vs 84

Hardware

qwen3.5-35b-a3b-t4… ornith-1.5-35b
MachineDell Inc. PowerEdge R820Micro-Star International Co., Ltd. MS-7E51
CPUIntel Xeon® E5-4650 v2AMD Ryzen 7 9700X 8-Core Processor
Cores8016
RAM256 GB31 GB
GPUMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display AdapterNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5-35b-a3b-t4… ornith-1.5-35b
Tokens/sec17.280.4
First chunk845 ms24 ms
TTFT845 ms231 ms
Load time103.1 sN/A
Memory usage21.9 GB20.2 GB
Memory %9%65%

HW Fit Score Breakdown

qwen3.5-35b-a3b-t48-c8k…

Speed
16/50
TTFT
17/20
Memory
30/30

ornith-1.5-35b

Speed
50/50
TTFT
20/20
Memory
18/30

Quality

qwen3.5-35b-a3b-t48-c8k…

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

ornith-1.5-35b

Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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