Sarvam 105B
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M limegreenpeper1/sarvam-105B-GGUF | 59.80 GiB | 14 | unknown | 64 GB GPU (cache unknown) | HF files |
| Q8_0 limegreenpeper1/sarvam-105B-GGUF | 105 GiB | 24 | unknown | 128 GB GPU (cache unknown) | HF files |
No verified file: Q5_K_M, FP16, BF16, 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
8.8 AA estimate
Variant: Sarvam 105B (High) · observed 2026-10-17 · source
Rank #68 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.