Qwen3.8-2.4T-A95B
Released2026-08-12Size2.4T · 95B activeArchitecturehybrid linear attnLicenseqwen3.8-maxAA rank#7 of 75
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q8_0 unsloth/Qwen3.8-2.4T-A95B-GGUF | 2,422 GiB | 56 | 2,423 GiB+ | over 192 GB GPU | HF files |
| BF16 unsloth/Qwen3.8-2.4T-A95B-GGUF | 4,557 GiB | 140 | 4,559 GiB+ | over 192 GB GPU | HF files |
No verified file: Q4_K_M, Q5_K_M, FP16, MLX 4-bit, MLX 8-bit. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.
Quality
Artificial Analysis Intelligence Index
39.9
Variant: Qwen3.8 2.4T A95B · observed 2026-10-17 · source
Rank #7 of 75 researched 2026 models.
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 0
No reported measurement yet. Submit one.