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

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

Global Score
81 vs 83
Hardware Fit
63 vs 100
Quality Score
88 vs 76

Hardware

qwen3.5-35b-a3b-t4… qwen3.5:4b
MachineDell Inc. PowerEdge R820MacBook Pro
CPUIntel Xeon® E5-4650 v2Apple M1 Max
Cores8010
RAM256 GB32 GB
GPUMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display AdapterApple M1 Max
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5-35b-a3b-t4… qwen3.5:4b
Tokens/sec17.232.4
First chunk845 ms306 ms
TTFT845 ms306 ms
Load time103.1 s2.7 s
Memory usage21.9 GB6.5 GB
Memory %9%20%

HW Fit Score Breakdown

qwen3.5-35b-a3b-t48-c8k…

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

qwen3.5:4b

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

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

qwen3.5:4b

Reasoning
16/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5-35b-a3b-t4… details | View qwen3.5:4b 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