Models
Size · speed · intelligence.
The field on one axis. Cyan marks what Conifer runs locally.
Intelligence
Artificial Analysis Intelligence Index v4.0 · higher is better · Artificial Analysis · 56 models
- 65Claude Fable 5: 65 index
- 61Claude Opus 4.8: 61 index
- 60GPT-5.5: 60 index
- 57Claude Opus 4.7: 57 index
- 54Kimi K2.6: 54 index
- 52DeepSeek V4 Pro: 52 index
- 48GPT-5.1: 48 index
- 48Gemini 3 Pro: 48 index
- 45GPT-5: 45 index
- 43Claude Opus 4.5: 43 index
- 42Grok 4: 42 index
- 41Kimi K2 Thinking: 41 index
- 37Claude Sonnet 4.5: 37 index
- 35Gemini 2.5 Pro: 35 index
- 33.3gpt-oss 120B: 33.3 index
- 33GLM-4.6: 33 index
- 32.1DeepSeek V3.2: 32.1 index
- 31.4Qwen3 Max: 31.4 index
- 27DeepSeek R1 0528: 27 index
- 25Qwen3 235B: 25 index
- 24.7Qwen3 VL 32B: 24.7 index
- 24.6Nova 2.0 Lite: 24.6 index
- 24.5gpt-oss 20B: 24.5 index
- 24.4MiniMax M1: 24.4 index
- 24.4GPT-5.4 nano: 24.4 index
- 24.3Gemini 2.5 Flash: 24.3 index
- 24.3Nemotron 3 Nano: 24.3 index
- 23.7o1-preview: 23.7 index
- 23.6Grok 4.1 Fast: 23.6 index
- 23.3GPT-5.4 mini: 23.3 index
- 23.2Nova 2.0 Omni: 23.2 index
- 23.1Grok 4 Fast: 23.1 index
- 23.1Nova 2.0 Pro: 23.1 index
- 23GLM-4.5 Air: 23 index
- 22.9GPT-4.1 mini: 22.9 index
- 22.8Mistral Large 3: 22.8 index
- 22.6Qwen3.5 4B: 22.6 index, runs locally on Conifer
- 22.4Qwen3 30B A3B: 22.4 index, runs locally on Conifer
- 22.3DeepSeek V3 0324: 22.3 index
- 22Devstral 2: 22 index
- 18.8Mistral Medium 3: 18.8 index
- 18.4Llama 4 Maverick: 18.4 index
- 17Qwen3 32B: 17 index, runs locally on Conifer
- 17R1 Distill 32B: 17 index, runs locally on Conifer
- 16Qwen3 14B: 16 index, runs locally on Conifer
- 16R1 Distill 14B: 16 index, runs locally on Conifer
- 14Llama 3.3 70B: 14 index
- 14Qwen3 4B: 14 index, runs locally on Conifer
- 13Qwen3 8B: 13 index, runs locally on Conifer
- 13Qwen2.5 32B: 13 index, runs locally on Conifer
- 13Qwen2.5 Coder 32B: 13 index, runs locally on Conifer
- 12Llama 3.1 8B: 12 index, runs locally on Conifer
- 10.4Phi-4: 10.4 index, runs locally on Conifer
- 10.3Gemma 3 27B: 10.3 index
- 9Gemma 3 12B: 9 index, runs locally on Conifer
- 6Gemma 3 4B: 6 index, runs locally on Conifer
how to read this
The whole Artificial Analysis field on one axis, and lit in cyan: the open models Conifer runs locally.
On the Intelligence composite the cloud giants tower; flip to GPQA, AIME or coding to watch the laptop-sized models punch far above their weight.
methodology & sources
Published figures, cross-checked against Artificial Analysis and each model's own technical report (snapshot Jun 2026).
Intelligence is the live Artificial Analysis Intelligence Index v4.0 (a 10-eval composite); capability scores are reasoning / thinking mode, no external tools, and benchmark versions vary by lab.
“Runs locally” marks the open weights in Conifer's catalogue that fit a personal machine; larger open models (Kimi, DeepSeek V3/V4, gpt-oss 120B, Qwen3 235B) sit in the field.
| model | size | tok/s | intelligence |
|---|---|---|---|
| Llama | |||
| Llama 3.2 1B | 1.2B | 299 | 49.3 |
| Llama 3.2 3B | 3.2B | 118 | 63.4 |
| Llama 3.1 8B | 8.0B | 49 | 69.4 |
| Hermes 3 · Llama 3.1 8B | 8.0B | ~49 | 64.8 |
| Qwen 3 | |||
| Qwen 3 0.6B | 0.6B | ~290 | 52.8 |
| Qwen 3 1.7B | 1.7B | ~165 | 62.6 |
| Qwen 3 4B | 4.0B | 90 | 73.0 |
| Qwen 3 4B Instruct 2507 | 4.0B | ~90 | · |
| Qwen 3 8B | 8.2B | 46 | 76.9 |
| Qwen 3 14B | 14.8B | ~25 | 81.1 |
| Qwen 3 32B | 32.8B | ~12 | 83.6 |
| Qwen 3 30B A3B 2507 | 30.5B · 3B active | · | 87.1 |
| Qwen 3 Coder 30B A3B | 30.5B · 3B active | · | · |
| Qwen 2.5 | |||
| Qwen 2.5 0.5B | 0.5B | 288 | 47.5 |
| Qwen 2.5 1.5B | 1.5B | 166 | 60.9 |
| Qwen 2.5 3B | 3.1B | 89 | 65.6 |
| Qwen 2.5 7B | 7.6B | 53 | 74.2 |
| Qwen 2.5 14B | 14.7B | ~27 | 79.7 |
| Qwen 2.5 Coder 1.5B | 1.5B | ~166 | 53.6 |
| Qwen 2.5 Coder 7B | 7.6B | ~53 | 68.0 |
| Gemma | |||
| Gemma 2 2B | 2.6B | 138 | 51.3 |
| Gemma 2 9B | 9.2B | ~41 | 71.3 |
| Gemma 3 4B | 4.3B | 66 | 59.6 |
| Gemma 4 12B | 11.9B | 15 | 74.5 |
| DeepSeek | |||
| R1 Distill Qwen 1.5B | 1.8B | ~166 | · |
| R1 Distill Qwen 7B | 7.6B | ~53 | · |
| R1 Distill Llama 8B | 8.0B | ~49 | · |
| R1 Distill Qwen 14B | 14.8B | ~27 | · |
| R1 Distill Qwen 32B | 32.8B | ~12 | · |
| DeepSeek V2 Lite | 15.7B | · | 55.7 |
| Phi | |||
| Phi 3.5 Mini | 3.8B | ~78 | 69.0 |
measurement notes
tok/s: decode, Apple M3 Max, Q4_K_M, 512-token prompt; ~ projected from a measured sibling. intelligence: MMLU 5-shot, as published. · marks not measured / not published.