All models › zai
Arena score1440#76 of 416 in Chat, paid models included
Size356.8 B37.6 B active per token (mixture of experts)
4-bit download216 GBweights only, Q4_K_M
Max context198Ktokens, from the model config
Where to use it for free
- The lab's own chat: chat.z.ai (free with daily limits)
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
Arena scores
Rank among all models, paid ones included. Source: Arena leaderboard dataset.
Speed on popular hardware
| Hardware | GPU memory | Fits? | Speed |
|---|---|---|---|
| RTX 3060 12 GB | 12 GB | Does not fit | — |
| RTX 4060 Ti 16 GB | 16 GB | Does not fit | — |
| RTX 3090 | 24 GB | Does not fit | — |
| RTX 4090 | 24 GB | Does not fit | — |
| RTX 5090 | 32 GB | Does not fit | — |
| RX 7900 XTX | 24 GB | Does not fit | — |
| 2 × RTX 3090 | 48 GB | Does not fit | — |
| 4 × RTX 3090 | 96 GB | Does not fit | — |
| Mac M4 Max 128 GB | 96 GB | Does not fit | — |
| Ryzen AI Max+ 395 128 GB | 96 GB | Does not fit | — |
| 8 × H100 SXM | 640 GB | Fits in GPU | 55 tok/s |
Estimate at 4-bit with 32K context, 64 GB of DDR5 for offload. Speed ≈ memory bandwidth × 70% ÷ data read per token; real numbers vary by about ±30%.
GPU memory needed
| Level | 8K context | 32K context | 128K context | Quality vs full |
|---|---|---|---|---|
| Q3_K_M | 182 GB | 191 GB | 228 GB | +4.7% noticeable loss |
| Q4_K_M | 220 GB | 229 GB | 266 GB | +1.2% very small loss |
| Q5_K_M | 257 GB | 267 GB | 304 GB | +0.4% near-lossless |
| Q6_K | 296 GB | 306 GB | 343 GB | +0.2% near-lossless |
| Q8_0 | 383 GB | 392 GB | 429 GB | ≈ 0% same as full |
| F16 | 717 GB | 727 GB | 764 GB | ≈ 0% same as full |
Weights + context cache (from the model's architecture) + runtime. Quality: increase in perplexity against the full model, from llama.cpp tests, scaled by model size. Simulate your own setup.
Chat score over time
145015001550
MayJunJulAugSeptOct
GLM-4.6 1440Best paid model
Arena score from 17 Apr 2026 to 15 Oct 2026.
Similar free models in Chat
- Inkling 1441
- Qwen3.8-27B 1441 · 27.8 B
- Hy3 1438 · 298.8 B
- Qwen3.5-397B-A17B 1438 · 403.4 B
- Gemma 4 31B 1443 · 31.3 B
- kimi-k2.5-thinking 1445