Models
Everytrackedmodel.
One page per model: what it needs in memory, where it runs, and how it moves on the radar — all from measured readings and the same fit engine as the finder.
| # | Model | Measured file | Heat | Runs comfortably at 8K |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibaba Qwen · general, coding, agents, research | 27.8B · Q4_K_M · 15.3 GB | 82 | 7 of 14 |
| 2 | gpt-oss 120BOpenAI · general, research, agents | 117B MoE · Q4_K_M · 58.5 GB | 77 | 1 of 14 |
| 3 | GLM-5.3-FlashZhipu AI · general, coding, agents | 321B · Q4_K · 186 GB | 76 | 0 of 14 |
| 4 | Llama 3.1 8BMeta · general, coding | 8B · Q4_K_M · 4.6 GB | 76 | unknown · attention shape unpublished |
| 5 | Llama 3.2 3BMeta · general | 3B · Q4_K_M · 1.9 GB | 76 | unknown · attention shape unpublished |
| 6 | Qwen3.8 Flash-NextAlibaba Qwen · general, coding, agents | 180B MoE · Q4_K · 103.7 GB | 73 | 0 of 14 |
| 7 | GLM-5.3Zhipu AI · general, agents, research | 753B · Q4_K · 435.2 GB | 72 | 0 of 14 |
| 8 | gpt-oss 20BOpenAI · general, agents, research | 20.9B MoE · Q4_K_M · 10.8 GB | 70 | 12 of 14 |
| 9 | Gemma 4 31BGoogle · general, research | 31.3B · Q4_K_M · 17.1 GB | 68 | 5 of 14 |
| 10 | Ling 3.0 TinyInclusionAI · general, agents | 7.9B MoE · Q4_K_M · 4.5 GB | 66 | 14 of 14 |
| 11 | Ornith 1.5 35B-A3BOrnith AI · general, coding, agents | 36B MoE · Q4_K_M · 20.2 GB | 62 | 5 of 14 |
| 12 | Gemma 4 12BGoogle · general, research | 12B · Q4_K_M · 6.6 GB | 62 | 14 of 14 |
| 13 | Qwen3 8BAlibaba Qwen · general, coding, agents | 8.2B · Q4_K_M · 4.7 GB | 62 | 14 of 14 |
| 14 | Ornith 1.5 9BOrnith AI · general, coding | 9.7B · Q4_K_M · 5.4 GB | 60 | 14 of 14 |
| 15 | Gemma 4 E4BGoogle · general | 8B · Q4_K_M · 4.6 GB | 60 | 14 of 14 |
| 16 | Qwen3 0.6BAlibaba Qwen · general | 0.6B · Q8_0 · 0.6 GB | 57 | 14 of 14 |
| 17 | Granite 4.2 8BIBM · general, coding, agents | 8.8B · Q4_K_M · 5 GB | 57 | 14 of 14 |
| 18 | DeepSeek-V4-FlashDeepSeek · general, coding, research | 304B MoE · Q4_K · 144.4 GB | 56 | 0 of 14 |
| 19 | Llama 3.3 70BMeta · general, research, agents | 70.6B · Q4_K_M · 39.6 GB | 53 | 2 of 14 |
| 20 | Gemma 4 26B-A4BGoogle · general, research | 25.8B MoE · Q4_K_M · 15.8 GB | 53 | 7 of 14 |
| 21 | DeepSeek-V4-ProDeepSeek · research, coding, agents | 1650B MoE · Q4_K · 791.3 GB | 52 | 0 of 14 |
| 22 | Qwen3 4BAlibaba Qwen · general, coding | 4B · Q4_K_M · 2.3 GB | 50 | 14 of 14 |
| 23 | Devstral Small 2 24BMistral AI · coding, agents | 24B · Q4_K_M · 13.3 GB | 50 | 7 of 14 |
| 24 | Qwen3-Coder 30B-A3BAlibaba Qwen · coding, agents | 30.5B MoE · Q4_K_M · 17.3 GB | 49 | 5 of 14 |
| 25 | Granite 4.2 30BIBM · general, coding, agents | 29.3B · Q4_K_M · 16.5 GB | 49 | 5 of 14 |
| 26 | Qwen3.8 2.4T-A95BAlibaba Qwen · general, agents, research | 2.4T-A95B · IQ4_XS · 1220.8 GB | 48 | 0 of 14 |
| 27 | Qwen3 32BAlibaba Qwen · general, coding, research, agents | 32.8B · Q4_K_M · 18.4 GB | 48 | 5 of 14 |
| 28 | Granite 4.2 3BIBM · general, agents | 3.7B · Q4_K_M · 2.1 GB | 47 | 14 of 14 |
| 29 | GLM-4.7-FlashZhipu AI · coding, agents | 31.2B MoE · Q4_K_M · 17.1 GB | 44 | 7 of 14 |
| 30 | LFM2.5 2.6BLiquid AI · general, agents | 2.7B · Q4_K_M · 1.6 GB | 42 | 14 of 14 |
| 31 | Ornith 1.5 397BOrnith AI · general, coding, research | 403B MoE · Q4_K_M · 227.5 GB | 40 | 0 of 14 |
| 32 | GLM-5.2Zhipu AI · coding, agents, research | 753B MoE · Q4_K_M · 433.8 GB | 39 | 0 of 14 |
| 33 | KAT-Coder V2.5Kwaipilot · coding, agents | 34.7B MoE · Q4_K_M · 19.9 GB | 38 | 5 of 14 |
| 34 | Qwen3 14BAlibaba Qwen · general, coding, research | 14.8B · Q4_K_M · 8.4 GB | 37 | 12 of 14 |
| 35 | Mistral Small 3.2Mistral AI · general, agents | 24B · Q4_K_M · 13.3 GB | 37 | 7 of 14 |
| 36 | LFM2.5 8B-A1BLiquid AI · general, agents | 8.5B MoE · Q4_K_M · 4.8 GB | 34 | 14 of 14 |
| 37 | Phi-4 MiniMicrosoft · general | 3.8B · Q4_K_M · 2.3 GB | 34 | 14 of 14 |
| 38 | Nemotron Nano 9B v2NVIDIA · general, research | 8.9B · Q4_K_M · 6.1 GB | 33 | 14 of 14 |
| 39 | Ling 3.0 FlashInclusionAI · general, agents | 127B MoE · Q4_K_M · 70.1 GB | 30 | 1 of 14 |
| 40 | Qwen3-Coder NextAlibaba Qwen · coding, agents | 79.7B MoE · Q4_K_M · 45.1 GB | 27 | 2 of 14 |
| 41 | Hy3Tencent · general, research | 299B MoE · Q4_K_M · 166.3 GB | 26 | 0 of 14 |
| 42 | Gemma 3 27BGoogle · general, research | 27.4B · Q4_K_M · 15.4 GB | 22 | 7 of 14 |
| 43 | Qwen AgentWorld 35B-A3BAlibaba Qwen · agents, coding | 34.7B MoE · Q4_K_M · 20.6 GB | 21 | 5 of 14 |
| 44 | GLM-4.5-AirZhipu AI · coding, agents, general, research | 110B MoE · Q4_K_M · 68 GB | 19 | 1 of 14 |
| 45 | LFM2.5 1.2BLiquid AI · general | 1.2B · Q4_K_M · 0.7 GB | 17 | 14 of 14 |
Comfortable = EXCELLENT or GOOD on that device at 8K context. Models without a measured open-weights file show no fit.