Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

internlm2_5-1_8b-chat

LM-STUDIO GGUF

internlm2 · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score
65 vs 55
Hardware Fit
73 vs 60
Quality Score
62 vs 53

Hardware

qwen3.5:4b internlm2_5-1_8b-c…
MachineAZW GTR ProLENOVO 20BUS00700
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-5300U
Cores324
RAM125 GB16 GB
GPUAMD Radeon 8060SIntel(R) HD Graphics 5500
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:4b internlm2_5-1_8b-c…
Tokens/sec45.76.6
First chunk180 ms3037 ms
TTFT30.0 s3.0 s
Load time5.3 sN/A
Memory usage16.2 GB1.1 GB
Memory %13%7%

HW Fit Score Breakdown

qwen3.5:4b

Speed
43/50
TTFT
0/20
Memory
30/30

internlm2_5-1_8b-chat

Speed
23/50
TTFT
16/20
Memory
21/30

Quality

qwen3.5:4b

Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong

internlm2_5-1_8b-chat

Reasoning
10/20
Coding
9/20
Instruction
14/20
Structured
10/15
Math
5/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
View qwen3.5:4b details | View internlm2_5-1_8b-c… 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