Compare models on your machine
Not generic leaderboards: every model is rated for your hardware, your tool and your workload — so you can see which one will actually feel better to use.
MacBook Pro M4 Pro 48 GB · Agentic coding / medium repository
- Recursive Flint (40B-A2.5B)MXFP4 · LM StudioComfortableSpeed 65–90 tok/sUses 22 GBFree 15 GB
- Qwen3.6 35B-A3B5-bit · LM StudioComfortableSpeed 50–70 tok/sUses 25 GBFree 12 GB
- Qwen3.5 35B-A3B5-bit · LM StudioComfortableSpeed 50–70 tok/sUses 25 GBFree 12 GB
- GLM-4.6V-Flash (10B)6-bit · LM StudioAcceptableSpeed 18–25 tok/sUses 10 GBFree 26 GB
| Model | Confidence | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Recursive Flint (40B-A2.5B)MXFP4 · LM Studio | Comfortable | 22 GB | 15 GB | Excellent65–90 tok/s | Comfortable | 128K | Strong | Strong | Medium confidence |
| Qwen3.6 35B-A3B5-bit · LM Studio | Comfortable | 25 GB | 12 GB | Excellent50–70 tok/s | Comfortable | 128K | Strong | Strong | Medium confidence |
| Qwen3.5 35B-A3B5-bit · LM Studio | Comfortable | 25 GB | 12 GB | Excellent50–70 tok/s | Comfortable | 128K | Good | Good | Medium confidence |
| GLM-4.6V-Flash (10B)6-bit · LM Studio | Acceptable | 10 GB | 26 GB | Adequate18–25 tok/s | Slow | 128K | Fair | Fair | Medium confidence |
GLM-4.6V-Flash (10B)
6-bit · LM Studio
Usable for agentic coding, but expect compromises: ingesting a prompt of 18K tokens takes ≈85 s and each step ≈35 s; across ~25 calls a task takes ≈17 min; generation (18–25 tok/s) is adequate but not ideal for agentic coding.
≈26 GB headroom
18–25 tok/s
≈85 s first prompt
32K context
Official
Poorly suited
Recursive Flint (40B-A2.5B)
MXFP4 · LM Studio
Yes — this should be comfortable for agentic coding.
≈15 GB headroom
65–90 tok/s
≈20 s first prompt
32K context
Official
Suited
Qwen3.6 35B-A3B
5-bit · LM Studio
Yes — this should be comfortable for agentic coding.
≈12 GB headroom
50–70 tok/s
≈20 s first prompt
32K context
Official
Suited
Qwen3.5 35B-A3B
5-bit · LM Studio
Yes — this should be comfortable for agentic coding.
≈12 GB headroom
50–70 tok/s
≈20 s first prompt
32K context
Official
Suited