Qwen3.5-35B-A3B
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M unsloth/Qwen3.5-35B-A3B-GGUF | 20.50 GiB | 1 | 21.7 GiB+ | 24 GB GPU | HF files |
| Q5_K_M unsloth/Qwen3.5-35B-A3B-GGUF | 24.45 GiB | 1 | 25.6 GiB+ | 32 GB GPU | HF files |
| Q8_0 unsloth/Qwen3.5-35B-A3B-GGUF | 34.37 GiB | 1 | 35.5 GiB+ | 48 GB GPU | HF files |
| MLX 4-bit mlx-community/Qwen3.5-35B-A3B-4bit | 18.99 GiB | 4 | 20.1 GiB+ | 32 GB Mac | HF files |
| MLX 8-bit mlx-community/Qwen3.5-35B-A3B-8bit | 35.13 GiB | 8 | 36.3 GiB+ | 64 GB Mac | HF files |
No verified file: FP16. 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 20
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database
Community threads
- Given a search question, return reasoning and content("\n\n") with no tool calls in first turn ending with finish_reason==stop. Hugging Face · 2026-06-02
- Compact tool-rendering template — 49% fewer prompt tokens Hugging Face · 2026-04-12
Qualitative signals only; titles are not verified claims.