Qwen3.5-2B
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M unsloth/Qwen3.5-2B-GGUF | 1.19 GiB | 1 | 2.3 GiB+ | 8 GB GPU | HF files |
| Q5_K_M unsloth/Qwen3.5-2B-GGUF | 1.34 GiB | 1 | 2.4 GiB+ | 8 GB GPU | HF files |
| Q8_0 unsloth/Qwen3.5-2B-GGUF | 1.87 GiB | 1 | 3.0 GiB+ | 8 GB GPU | HF files |
| FP16 AaryanK/Qwen3.5-2B-GGUF | 3.52 GiB | 1 | 4.6 GiB+ | 8 GB GPU | HF files |
| MLX 4-bit mlx-community/Qwen3.5-2B-4bit | 1.60 GiB | 1 | 2.7 GiB+ | 8 GB Mac | HF files |
| MLX 8-bit mlx-community/Qwen3.5-2B-8bit | 2.48 GiB | 1 | 3.6 GiB+ | 8 GB Mac | HF files |
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
Unknown
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.
Community threads
- Run Qwen 3.5 in C under 8 GB RAM Hugging Face · 2026-08-30
- Listed on OpenModelMap Hugging Face · 2026-08-08
Qualitative signals only; titles are not verified claims.