Qwen3.5 Qwen
quantized: 2,780adapter: 3,059finetune: 5,284merge: 103
Which ones matter
- Qwen3.5-9B Qwen/Qwen3.5-9B Highest candidate score in the family (127.907); 6 providers serving it.
- Qwen3.5-0.8B Qwen/Qwen3.5-0.8B Smallest member with a hosted provider (873M, 1 providers).
- Qwen3.5-35B-A3B-FP8 Qwen/Qwen3.5-35B-A3B-FP8 Most downloaded quantization (12,399,466 all-time, by Qwen).
Picks are rule-based from observed data (score, downloads, size, hosting); they are not quality verdicts.
Members 13
| # | Model | Org | Role | Params | Band | MoE | License | Context | Providers | Price from | Likes | Likes 7d | Downloads 30d | Modified |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 13 | Qwen3.5-9B | Qwen | Fine-tuned from Qwen/Qwen3.5-9B-Bas… | 9.65B | L | dense | Apache 2.0 | 256K | 6 | $0.08 | 2.2k | +49 | 6.3M | 2026-03-02 |
| 22 | Qwen3.5-397B-A17B | Qwen | Original model | 403B / 17B | XXL | MoE | Apache 2.0 | 256K | 7 | $0.39 | 1.6k | +7 | 733.5k | 2026-04-24 |
| 36 | Qwen3.5-35B-A3B | Qwen | Fine-tuned from Qwen/Qwen3.5-35B-A3… | 36.0B / 3B | XL | MoE | Apache 2.0 | 256K | 4 | $0.07 | 1.5k | +8 | 1.5M | 2026-04-24 |
| 40 | Qwen3.5-27B | Qwen | Original model | 27.8B | L | dense | Apache 2.0 | 256K | 4 | $0.20 | 1.1k | +6 | 1.7M | 2026-04-24 |
| 46 | Qwen3.5-4B | Qwen | Fine-tuned from Qwen/Qwen3.5-4B-Bas… | 4.66B | M | dense | Apache 2.0 | 256K | 2 | — | 1.1k | +28 | 7.5M | 2026-03-02 |
| 89 | Qwen3.5-122B-A10B | Qwen | Original model | 125B / 10B | XXL | MoE | Apache 2.0 | 256K | 3 | $0.26 | 644 | +6 | 806.8k | 2026-04-24 |
| 100 | Qwen3.5-2B | Qwen | Fine-tuned from Qwen/Qwen3.5-2B-Bas… | 2.27B | M | dense | Apache 2.0 | 256K | 2 | — | 454 | +8 | 3.1M | 2026-03-02 |
| 104 | Qwen3.5-0.8B | Qwen | Fine-tuned from Qwen/Qwen3.5-0.8B-B… | 873M | S | dense | Apache 2.0 | 256K | 1 | — | 784 | +11 | 3.5M | 2026-03-02 |
| 439 | Qwen3.5-0.8B-Base | Qwen | Original model | 873M | S | dense | Apache 2.0 | 256K | 0 | — | 132 | +9 | 475.1k | 2026-04-23 |
| 467 | Qwen3.5-4B-Base | Qwen | Original model | 4.66B | M | dense | Apache 2.0 | 256K | 0 | — | 121 | +5 | 724.6k | 2026-04-23 |
| 517 | Qwen3.5-9B-Base | Qwen | Original model | 9.65B | L | dense | Apache 2.0 | 256K | 0 | — | 134 | +3 | 362.7k | 2026-04-23 |
| 550 | Qwen3.5-2B-Base | Qwen | Original model | 2.27B | M | dense | Apache 2.0 | 256K | 0 | — | 105 | +2 | 303.5k | 2026-04-23 |
| 762 | Qwen3.5-35B-A3B-Base | Qwen | Original model | 36.0B / 3B | XL | MoE | Apache 2.0 | — | 0 | — | 157 | — | 116.3k | 2026-04-23 |
Variants 150 shown of 11,226
Quantizations, fine-tunes, merges, and adapters of any member, ranked by downloads + likes. Filter by relation, quant family, or size band.
| Variant | Of | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|---|
| Qwen/Qwen3.5-35B-A3B-FP8 | Qwen/Qwen3.5-35B-A3B | quantized | -FP8 | 36.0B | XL | apache-2.0 | Qwen | 165 | 12.4M |
| unsloth/Qwen3.5-9B-GGUF | Qwen/Qwen3.5-9B | quantized | GGUF | — | — | apache-2.0 | unsloth | 1k | 10.1M |
| Qwen/Qwen3.5-122B-A10B-FP8 | Qwen/Qwen3.5-122B-A10B | quantized | -FP8 | 125B | XXL | apache-2.0 | Qwen | 130 | 8M |
| unsloth/Qwen3.5-4B-GGUF | Qwen/Qwen3.5-4B | quantized | GGUF | — | — | apache-2.0 | unsloth | 507 | 7.6M |
| Qwen/Qwen3.5-27B-FP8 | Qwen/Qwen3.5-27B | quantized | -FP8 | 27.8B | L | apache-2.0 | Qwen | 145 | 7.4M |
| Qwen/Qwen3.5-397B-A17B-FP8 | Qwen/Qwen3.5-397B-A17B | quantized | -FP8 | 403B | XXL | apache-2.0 | Qwen | 193 | 6.7M |
| HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive | Qwen/Qwen3.5-9B | quantized | GGUF | — | — | apache-2.0 | HauhauCS | 2.4k | 5.8M |
| unsloth/Qwen3.5-35B-A3B-GGUF | Qwen/Qwen3.5-35B-A3B | quantized | GGUF | — | — | apache-2.0 | unsloth | 879 | 5.5M |
| Qwen/Qwen3.5-35B-A3B-GPTQ-Int4 | Qwen/Qwen3.5-35B-A3B | quantized | GPTQ | 36.0B | XL | apache-2.0 | Qwen | 99 | 5.2M |
| lmstudio-community/Qwen3.5-9B-GGUF | Qwen/Qwen3.5-9B | quantized | GGUF | — | — | apache-2.0 | lmstudio-community | 75 | 5.1M |
| QuantTrio/Qwen3.5-9B-AWQ | Qwen/Qwen3.5-9B | quantized | AWQ | 9.65B | L | apache-2.0 | QuantTrio | 28 | 4.8M |
| cyankiwi/Qwen3.5-4B-AWQ-4bit | Qwen/Qwen3.5-4B | quantized | AWQ | 4.66B | M | apache-2.0 | cyankiwi | 25 | 4.3M |
| lmstudio-community/Qwen3.5-9B-MLX-4bit | Qwen/Qwen3.5-9B | quantized | MLX | 9.41B | L | apache-2.0 | lmstudio-community | 7 | 3.2M |
| nvidia/Qwen3.5-397B-A17B-NVFP4 | Qwen/Qwen3.5-397B-A17B | quantized | NVFP4 | 204B | XXL | apache-2.0 | nvidia | 113 | 3.1M |
| cyankiwi/Qwen3.5-9B-AWQ-4bit | Qwen/Qwen3.5-9B | quantized | AWQ | 9.65B | L | apache-2.0 | cyankiwi | 38 | 3.1M |
| HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive | Qwen/Qwen3.5-35B-A3B | quantized | GGUF | — | — | apache-2.0 | HauhauCS | 1.5k | 2.9M |
| lmstudio-community/Qwen3.5-9B-MLX-8bit | Qwen/Qwen3.5-9B | quantized | MLX | 9.41B | L | apache-2.0 | lmstudio-community | 3 | 3M |
| unsloth/Qwen3.5-27B-GGUF | Qwen/Qwen3.5-27B | quantized | GGUF | — | — | apache-2.0 | unsloth | 506 | 2.9M |
| cyankiwi/Qwen3.5-27B-AWQ-4bit | Qwen/Qwen3.5-27B | quantized | AWQ | 27.8B | L | apache-2.0 | cyankiwi | 41 | 2.8M |
| nvidia/Qwen3.5-122B-A10B-NVFP4 | Qwen/Qwen3.5-122B-A10B | quantized | NVFP4 | 64.6B | XL | apache-2.0 | nvidia | 62 | 2.6M |
| unsloth/Qwen3.5-0.8B-GGUF | Qwen/Qwen3.5-0.8B | quantized | GGUF | — | — | apache-2.0 | unsloth | 243 | 2.4M |
| cyankiwi/Qwen3.5-35B-A3B-AWQ-4bit | Qwen/Qwen3.5-35B-A3B | quantized | AWQ | 36.0B | XL | apache-2.0 | cyankiwi | 47 | 2.4M |
| Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | Qwen/Qwen3.5-27B | quantized | GGUF | — | — | apache-2.0 | Jackrong | 681 | 2.3M |
| AxionML/Qwen3.5-9B-NVFP4 | Qwen/Qwen3.5-9B | quantized | NVFP4 | 6.63B | M | apache-2.0 | AxionML | 22 | 2.2M |
| QuantTrio/Qwen3.5-27B-AWQ | Qwen/Qwen3.5-27B | quantized | AWQ | 27.8B | L | apache-2.0 | QuantTrio | 42 | 2.1M |
| unsloth/Qwen3.5-2B-GGUF | Qwen/Qwen3.5-2B | quantized | GGUF | — | — | apache-2.0 | unsloth | 164 | 2M |
| unsloth/Qwen3.5-122B-A10B-GGUF | Qwen/Qwen3.5-122B-A10B | quantized | GGUF | — | — | apache-2.0 | unsloth | 302 | 2M |
| Intel/Qwen3.5-122B-A10B-int4-AutoRound | Qwen/Qwen3.5-122B-A10B | quantized | int4 | 19.7B | L | — | Intel | 49 | 1.7M |
| numind/NuExtract3 | Qwen/Qwen3.5-4B | finetune | — | 4.54B | M | apache-2.0 | numind | 385 | 1.6M |
| bartowski/Qwen_Qwen3.5-35B-A3B-GGUF | Qwen/Qwen3.5-35B-A3B | quantized | GGUF | — | — | apache-2.0 | bartowski | 70 | 1.4M |
| Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | Qwen/Qwen3.5-9B | adapter | GGUF | — | — | apache-2.0 | Jackrong | 361 | 1.4M |
| bartowski/Qwen_Qwen3.5-4B-GGUF | Qwen/Qwen3.5-4B | quantized | GGUF | — | — | apache-2.0 | bartowski | 70 | 1.3M |
| unsloth/Qwen3.5-4B | Qwen/Qwen3.5-4B | finetune | — | 4.66B | M | apache-2.0 | unsloth | 28 | 1.3M |
| unsloth/Qwen3.5-9B | Qwen/Qwen3.5-9B | finetune | — | 9.65B | L | apache-2.0 | unsloth | 35 | 1.3M |
| HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive | Qwen/Qwen3.5-122B-A10B | quantized | GGUF | — | — | apache-2.0 | HauhauCS | 191 | 1.2M |
| Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | Qwen/Qwen3.5-4B | adapter | GGUF | — | — | apache-2.0 | Jackrong | 183 | 1.2M |
| huihui-ai/Huihui-Qwen3.5-27B-abliterated | Qwen/Qwen3.5-27B | finetune | — | 27.8B | L | apache-2.0 | huihui-ai | 161 | 1.2M |
| Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2 | Qwen/Qwen3.5-27B | adapter | — | 27.8B | L | apache-2.0 | Jackrong | 130 | 1.2M |
| bartowski/Qwen_Qwen3.5-0.8B-GGUF | Qwen/Qwen3.5-0.8B | quantized | GGUF | — | — | apache-2.0 | bartowski | 23 | 1.1M |
| lmstudio-community/Qwen3.5-35B-A3B-GGUF | Qwen/Qwen3.5-35B-A3B | quantized | GGUF | — | — | apache-2.0 | lmstudio-community | 26 | 1.1M |
| bartowski/Qwen_Qwen3.5-2B-GGUF | Qwen/Qwen3.5-2B | quantized | GGUF | — | — | apache-2.0 | bartowski | 28 | 1.1M |
| unsloth/Qwen3.5-397B-A17B-GGUF | Qwen/Qwen3.5-397B-A17B | quantized | GGUF | — | — | apache-2.0 | unsloth | 254 | 1.1M |
| cyankiwi/Qwen3.5-122B-A10B-AWQ-4bit | Qwen/Qwen3.5-122B-A10B | quantized | AWQ | 24.3B | L | apache-2.0 | cyankiwi | 43 | 1M |
| athrael-soju/colqwen3.5-4.5B-v3 | Qwen/Qwen3.5-4B | adapter | — | 4.54B | M | apache-2.0 | athrael-soju | 16 | 991.1k |
| Hcompany/Holo-3.1-35B-A3B-GGUF | Qwen/Qwen3.5-0.8B | quantized | GGUF | — | — | apache-2.0 | Hcompany | 53 | 983.2k |
| unsloth/Qwen3.5-2B | Qwen/Qwen3.5-2B | finetune | — | 2.27B | M | apache-2.0 | unsloth | 21 | 940k |
| autotrust/JEV-35B | Qwen/Qwen3.5-35B-A3B | finetune | — | 36.0B | XL | apache-2.0 | autotrust | 456 | 915.8k |
| RedHatAI/Qwen3.5-122B-A10B-NVFP4 | Qwen/Qwen3.5-122B-A10B | quantized | NVFP4 | 71.2B | XL | — | RedHatAI | 55 | 935.2k |
| QuantTrio/Qwen3.5-35B-A3B-AWQ | Qwen/Qwen3.5-35B-A3B | quantized | AWQ | 36.0B | XL | apache-2.0 | QuantTrio | 18 | 913.2k |
| txn545/Qwen3.5-122B-A10B-NVFP4 | Qwen/Qwen3.5-122B-A10B | quantized | NVFP4 | 64.4B | XL | apache-2.0 | txn545 | 24 | 864.5k |
| Sehyo/Qwen3.5-122B-A10B-NVFP4 | Qwen/Qwen3.5-122B-A10B | quantized | NVFP4 | 71.2B | XL | — | Sehyo | 69 | 846.4k |
| RedHatAI/Qwen3.5-9B-FP8-dynamic | Qwen/Qwen3.5-9B | quantized | -FP8 | 9.41B | L | apache-2.0 | RedHatAI | 12 | 835.1k |
| QuantTrio/Qwen3.5-4B-AWQ | Qwen/Qwen3.5-4B | quantized | AWQ | 4.66B | M | apache-2.0 | QuantTrio | 10 | 790.6k |
| lovedheart/Qwen3.5-9B-FP8 | Qwen/Qwen3.5-9B | quantized | -FP8 | 9.65B | L | apache-2.0 | lovedheart | 16 | 739.8k |
| Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF | Qwen/Qwen3.5-27B | adapter | GGUF | — | — | apache-2.0 | Jackrong | 621 | 704.7k |
| bartowski/Qwen_Qwen3.5-9B-GGUF | Qwen/Qwen3.5-9B | quantized | GGUF | — | — | apache-2.0 | bartowski | 117 | 720.1k |
| Intel/Qwen3.5-9B-int4-AutoRound | Qwen/Qwen3.5-9B | quantized | int4 | 3.52B | M | — | Intel | 27 | 695.5k |
| lovedheart/Qwen3.5-4B-FP8 | Qwen/Qwen3.5-4B | quantized | -FP8 | 4.66B | M | apache-2.0 | lovedheart | 7 | 684.7k |
| Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF | Qwen/Qwen3.5-9B | adapter | GGUF | — | — | apache-2.0 | Jackrong | 397 | 632.4k |
| lmstudio-community/Qwen3.5-4B-GGUF | Qwen/Qwen3.5-4B | quantized | GGUF | — | — | apache-2.0 | lmstudio-community | 32 | 646.4k |
| mudler/Qwen3.5-35B-A3B-APEX-GGUF | Qwen/Qwen3.5-35B-A3B | quantized | GGUF | — | — | apache-2.0 | mudler | 96 | 638.1k |
| unsloth/Qwen3.5-0.8B | Qwen/Qwen3.5-0.8B | finetune | — | 873M | S | apache-2.0 | unsloth | 22 | 624.7k |
| unsloth/Qwen3.5-9B-MTP-GGUF | Qwen/Qwen3.5-9B | quantized | GGUF | — | — | apache-2.0 | unsloth | 216 | 608.5k |
| autotrust/JEV-9B | Qwen/Qwen3.5-9B | finetune | — | 8.95B | M | apache-2.0 | autotrust | 94 | 611.3k |
| Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled | Qwen/Qwen3.5-9B | adapter | — | 9.65B | L | apache-2.0 | Jackrong | 61 | 608.8k |
| sanskar003/Qwen3.5-4B-AWQ | Qwen/Qwen3.5-4B | quantized | AWQ | 5.17B | M | apache-2.0 | sanskar003 | 7 | 597.2k |
| Comfy-Org/Qwen3.5 | Qwen/Qwen3.5-2B | finetune | — | — | — | apache-2.0 | Comfy-Org | 48 | 578.6k |
| bartowski/Qwen_Qwen3.5-27B-GGUF | Qwen/Qwen3.5-27B | quantized | GGUF | — | — | apache-2.0 | bartowski | 76 | 562.7k |
| unsloth/Qwen3.5-4B-MTP-GGUF | Qwen/Qwen3.5-4B | quantized | GGUF | — | — | apache-2.0 | unsloth | 106 | 560.5k |
| cyankiwi/Qwen3.5-2B-AWQ-4bit | Qwen/Qwen3.5-2B | quantized | AWQ | 2.27B | M | apache-2.0 | cyankiwi | 3 | 563.7k |
| unsloth/Qwen3.5-122B-A10B-MTP-GGUF | Qwen/Qwen3.5-122B-A10B | quantized | GGUF | — | — | apache-2.0 | unsloth | 109 | 456.1k |
| AxionML/Qwen3.5-35B-A3B-NVFP4 | Qwen/Qwen3.5-35B-A3B | quantized | NVFP4 | — | — | apache-2.0 | AxionML | 6 | 455k |
| mlx-community/Qwen3.5-9B-OptiQ-4bit | Qwen/Qwen3.5-9B | quantized | -4bit | 8.95B | M | apache-2.0 | mlx-community | 107 | 400.6k |
| tiny-random/qwen3.5-moe | Qwen/Qwen3.5-397B-A17B | finetune | — | 4.90M | S | — | tiny-random | 4 | 392.1k |
| mlx-community/Qwen3.5-9B-MLX-4bit | Qwen/Qwen3.5-9B | quantized | MLX | 9.41B | L | apache-2.0 | mlx-community | 187 | 377.2k |
| ig1/Qwen3.5-9B-NVFP4 | Qwen/Qwen3.5-9B | quantized | NVFP4 | 7.09B | M | apache-2.0 | ig1 | 3 | 380.8k |
| timteh673/Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUF | Qwen/Qwen3.5-397B-A17B | adapter | GGUF | — | — | apache-2.0 | timteh673 | 29 | 374.7k |
| cyankiwi/Qwen3.5-397B-A17B-AWQ-4bit | Qwen/Qwen3.5-397B-A17B | quantized | AWQ | 70.2B | XL | apache-2.0 | cyankiwi | 3 | 375.2k |
| apolo13x/Qwen3.5-9B-NVFP4 | Qwen/Qwen3.5-9B | quantized | NVFP4 | 7.54B | M | apache-2.0 | apolo13x | 1 | 360k |
| empero-ai/Qwythos-9B-Claude-Mythos-5-1M | Qwen/Qwen3.5-9B | finetune | — | 9.41B | L | apache-2.0 | empero-ai | 986 | 257.6k |
| hamishivi/Qwen3.5-9B | Qwen/Qwen3.5-9B-Base | finetune | — | 9.65B | L | apache-2.0 | hamishivi | 0 | 306.6k |
| Hyper-AI/Qwen3.5-9B-fp8 | Qwen/Qwen3.5-9B-Base | quantized | -fp8 | 9.65B | L | apache-2.0 | Hyper-AI | 3 | 301.7k |
| empero-ai/Qwen3.8-4B-Distill | Qwen/Qwen3.5-4B | finetune | — | 4.66B | M | apache-2.0 | empero-ai | 72 | 279.8k |
| unsloth/Qwen3.5-4B-Base | Qwen/Qwen3.5-4B-Base | finetune | — | 4.54B | M | apache-2.0 | unsloth | 12 | 277k |
| bartowski/Qwen_Qwen3.5-397B-A17B-GGUF | Qwen/Qwen3.5-397B-A17B | quantized | GGUF | — | — | apache-2.0 | bartowski | 12 | 275.4k |
| Intel/Qwen3.5-397B-A17B-int4-AutoRound | Qwen/Qwen3.5-397B-A17B | quantized | int4 | — | — | — | Intel | 19 | 259.2k |
| apolo13x/Qwen3.5-27B-NVFP4 | Qwen/Qwen3.5-27B | quantized | NVFP4 | 16.7B | L | apache-2.0 | apolo13x | 38 | 256.6k |
| hamishivi/Qwen3.5-4B | Qwen/Qwen3.5-4B-Base | finetune | — | 4.66B | M | apache-2.0 | hamishivi | 0 | 256.1k |
| mlx-community/Qwen3.5-4B-MLX-4bit | Qwen/Qwen3.5-4B | quantized | MLX | 4.54B | M | apache-2.0 | mlx-community | 47 | 246.6k |
| shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC | Qwen/Qwen3.5-122B-A10B | quantized | int4 | 21.1B | L | apache-2.0 | shieldstar | 7 | 245.7k |
| RedHatAI/Qwen3.5-9B-quantized.w8a8 | Qwen/Qwen3.5-9B | quantized | -quant | 9.41B | L | apache-2.0 | RedHatAI | 2 | 241.9k |
| RedHatAI/Qwen3.5-9B-quantized.w4a16 | Qwen/Qwen3.5-9B | quantized | -quant | 9.45B | L | apache-2.0 | RedHatAI | 9 | 239.4k |
| coder3101/Qwen3.5-27B-heretic | Qwen/Qwen3.5-27B | finetune | — | 27.4B | L | apache-2.0 | coder3101 | 74 | 235.6k |
| bartowski/Qwen_Qwen3.5-122B-A10B-GGUF | Qwen/Qwen3.5-122B-A10B | quantized | GGUF | — | — | apache-2.0 | bartowski | 30 | 235.6k |
| Alibaba-DAMO-Academy/RynnBrain1.1-2B | Qwen/Qwen3.5-2B | finetune | — | 2.21B | M | apache-2.0 | Alibaba-DAMO-Academy | 12 | 233.8k |
| kaitchup/Qwen3.5-27B-NVFP4 | Qwen/Qwen3.5-27B | quantized | NVFP4 | 19.1B | L | apache-2.0 | kaitchup | 13 | 225k |
| Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF | Qwen/Qwen3.5-4B | adapter | GGUF | — | — | apache-2.0 | Jackrong | 161 | 211.1k |
| lmstudio-community/Qwen3.5-2B-GGUF | Qwen/Qwen3.5-2B | quantized | GGUF | — | — | apache-2.0 | lmstudio-community | 9 | 217k |
| lmstudio-community/Qwen3.5-397B-A17B-MLX-8bit | Qwen/Qwen3.5-397B-A17B | quantized | MLX | 397B | XXL | apache-2.0 | lmstudio-community | 2 | 213k |
| QuantTrio/Qwen3.5-122B-A10B-AWQ | Qwen/Qwen3.5-122B-A10B | quantized | AWQ | 125B | XXL | apache-2.0 | QuantTrio | 29 | 211.6k |
| huihui-ai/Huihui-Qwen3.5-9B-abliterated | Qwen/Qwen3.5-9B | finetune | — | 9.65B | L | apache-2.0 | huihui-ai | 154 | 201.5k |
| prefeitura-rio/Rio-3.5-Open-397B | Qwen/Qwen3.5-397B-A17B | finetune | — | — | — | mit | prefeitura-rio | 329 | 191.5k |
| lmstudio-community/Qwen3.5-0.8B-GGUF | Qwen/Qwen3.5-0.8B | quantized | GGUF | — | — | apache-2.0 | lmstudio-community | 17 | 202.3k |
| lmstudio-community/Qwen3.5-27B-GGUF | Qwen/Qwen3.5-27B | quantized | GGUF | — | — | apache-2.0 | lmstudio-community | 20 | 191.1k |
| Qwen/Qwen3.5-397B-A17B-GPTQ-Int4 | Qwen/Qwen3.5-397B-A17B | quantized | GPTQ | 403B | XXL | apache-2.0 | Qwen | 43 | 187.2k |
| RedHatAI/Qwen3.5-4B-FP8-dynamic | Qwen/Qwen3.5-4B | quantized | -FP8 | 5.18B | M | apache-2.0 | RedHatAI | 6 | 183.1k |
| llmfan46/Qwen3.5-35B-A3B-uncensored-heretic | Qwen/Qwen3.5-35B-A3B | finetune | — | 35.1B | XL | apache-2.0 | llmfan46 | 18 | 179.2k |
| mlx-community/Qwen3.5-9B-4bit | Qwen/Qwen3.5-9B-Base | quantized | -4bit | 9.41B | L | apache-2.0 | mlx-community | 19 | 176.5k |
| lukey03/Qwen3.5-9B-abliterated-GGUF | Qwen/Qwen3.5-9B | quantized | GGUF | — | — | apache-2.0 | lukey03 | 92 | 171.9k |
| ggml-org/Qwen3.5-0.8B-GGUF | Qwen/Qwen3.5-0.8B | quantized | GGUF | — | — | apache-2.0 | ggml-org | 26 | 174.9k |
| z-lab/Qwen3.5-9B-PARO | Qwen/Qwen3.5-9B | quantized | — | 3.44B | M | apache-2.0 | z-lab | 52 | 169.9k |
| txn545/Qwen3.5-35B-A3B-NVFP4 | Qwen/Qwen3.5-35B-A3B | quantized | NVFP4 | — | — | apache-2.0 | txn545 | 7 | 167.9k |
| z-lab/Qwen3.5-27B-DFlash | Qwen/Qwen3.5-27B | finetune | — | 2.13B | M | apache-2.0 | z-lab | 111 | 161.9k |
| Intel/Qwen3.5-27B-int4-AutoRound | Qwen/Qwen3.5-27B | quantized | int4 | 6.81B | M | — | Intel | 21 | 159.1k |
| TokenRhythm/NeoHorse-1-4B | Qwen/Qwen3.5-4B | finetune | — | 4.21B | M | apache-2.0 | TokenRhythm | 2.6k | 32.3k |
| w-ahmad/Qwen3.5-9B-GGUF-MoQ | Qwen/Qwen3.5-9B | quantized | GGUF | — | — | mit | w-ahmad | 23 | 158.7k |
| Sehyo/Qwen3.5-35B-A3B-NVFP4 | Qwen/Qwen3.5-35B-A3B | quantized | NVFP4 | — | — | — | Sehyo | 41 | 154.1k |
| jica98/qwen3.5-4B-super-coder | Qwen/Qwen3.5-4B | quantized | GGUF | — | — | — | jica98 | 123 | 148.3k |
| nvidia/Qwen3.5-397B-A17B-NVFP4-V2 | Qwen/Qwen3.5-397B-A17B | quantized | NVFP4 | — | — | apache-2.0 | nvidia | 18 | 152.8k |
| mlx-community/Qwen3.5-2B-6bit | Qwen/Qwen3.5-2B-Base | quantized | — | 2.21B | M | apache-2.0 | mlx-community | 7 | 152k |
| cyankiwi/Qwen3.5-27B-AWQ-BF16-INT4 | Qwen/Qwen3.5-27B | quantized | AWQ | 27.8B | L | apache-2.0 | cyankiwi | 51 | 147.6k |
| unsloth/Qwen3.5-27B | Qwen/Qwen3.5-27B | finetune | — | 27.8B | L | apache-2.0 | unsloth | 16 | 147.5k |
| unsloth/Qwen3.5-35B-A3B | Qwen/Qwen3.5-35B-A3B | finetune | — | 36.0B | XL | apache-2.0 | unsloth | 16 | 145.5k |
| huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated | Qwen/Qwen3.5-35B-A3B | finetune | — | 36.0B | XL | apache-2.0 | huihui-ai | 405 | 125.5k |
| Hcompany/Holo3-35B-A3B | Qwen/Qwen3.5-35B-A3B | finetune | — | 35.1B | XL | apache-2.0 | Hcompany | 375 | 119.9k |
| unsloth/Qwen3.5-2B-MTP-GGUF | Qwen/Qwen3.5-2B | quantized | GGUF | — | — | apache-2.0 | unsloth | 46 | 130.1k |
| prism-ml/Ternary-Bonsai-2-9B-gguf | Qwen/Qwen3.5-9B | quantized | gguf | — | — | apache-2.0 | prism-ml | 125 | 124.2k |
| nicklas373/Qwen3.5-9B-AWQ | Qwen/Qwen3.5-9B | quantized | AWQ | 9.49B | L | — | nicklas373 | 0 | 127k |
| mlx-community/Qwen3.5-397B-A17B-8bit | Qwen/Qwen3.5-397B-A17B | quantized | -8bit | 397B | XXL | apache-2.0 | mlx-community | 5 | 119.1k |
| z-lab/Qwen3.5-9B-DFlash | Qwen/Qwen3.5-9B | finetune | — | 1.29B | S | apache-2.0 | z-lab | 51 | 112.4k |
| unsloth/Qwen3.5-35B-A3B-MTP-GGUF | Qwen/Qwen3.5-35B-A3B | quantized | GGUF | — | — | apache-2.0 | unsloth | 21 | 110.1k |
| apolo13x/Qwen3.5-35B-A3B-NVFP4 | Qwen/Qwen3.5-35B-A3B | quantized | NVFP4 | — | — | apache-2.0 | apolo13x | 16 | 110.1k |
| Jackrong/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | Qwen/Qwen3.5-0.8B | adapter | GGUF | — | — | apache-2.0 | Jackrong | 88 | 106.2k |
| QuantTrio/Qwen3.5-2B-AWQ | Qwen/Qwen3.5-2B-Base | quantized | AWQ | 2.27B | M | apache-2.0 | QuantTrio | 4 | 109.2k |
| Hcompany/Holo-3.1-35B-A3B | Qwen/Qwen3.5-0.8B | finetune | — | 35.1B | XL | apache-2.0 | Hcompany | 90 | 104.8k |
| unsloth/Qwen3.5-0.8B-MTP-GGUF | Qwen/Qwen3.5-0.8B | quantized | GGUF | — | — | apache-2.0 | unsloth | 40 | 103.7k |
| huihui-ai/Huihui-Qwen3.5-4B-abliterated | Qwen/Qwen3.5-4B | quantized | GGUF | 4.54B | M | apache-2.0 | huihui-ai | 47 | 102.7k |
| timteh673/Qwen3.5-122B-A10B-Opus-Reasoning-GGUF | Qwen/Qwen3.5-122B-A10B | adapter | GGUF | — | — | apache-2.0 | timteh673 | 10 | 103.7k |
| SoAIHQ/Qwen3.5-4B-GGUF | Qwen/Qwen3.5-4B | quantized | GGUF | — | — | apache-2.0 | SoAIHQ | 2 | 101.7k |
| prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption | Qwen/Qwen3.5-9B | quantized | GGUF | 9.41B | L | apache-2.0 | prithivMLmods | 64 | 98k |
| Ngixdev/OmniCoder-Qwen3.5-9B-Claude-4.6-Opus-Uncensored-v2-GGUF | Qwen/Qwen3.5-9B | adapter | GGUF | — | — | apache-2.0 | Ngixdev | 50 | 97.6k |
| z-lab/Qwen3.5-4B-DFlash | Qwen/Qwen3.5-4B | finetune | — | 634M | S | apache-2.0 | z-lab | 44 | 96.2k |
| cyankiwi/Qwen3.5-27B-AWQ-BF16-INT8 | Qwen/Qwen3.5-27B | quantized | AWQ | 27.8B | L | apache-2.0 | cyankiwi | 9 | 97.2k |
| mlx-community/Qwen3.5-9B-8bit | Qwen/Qwen3.5-9B-Base | quantized | -8bit | 9.41B | L | apache-2.0 | mlx-community | 20 | 95.7k |
| Zerul/Qwen3.5-0.8B-W4A16-AutoRound-AWQ | Qwen/Qwen3.5-0.8B | quantized | -W4A16 | 853M | S | — | Zerul | 0 | 92.6k |
| Jackrong/Qwen3.5-9B-Gemini-3.1-Pro-Reasoning-Distill-GGUF | Qwen/Qwen3.5-9B | quantized | GGUF | — | — | apache-2.0 | Jackrong | 50 | 89.8k |
| Tesslate/OmniCoder-9B | Qwen/Qwen3.5-9B | finetune | — | 9.41B | L | apache-2.0 | Tesslate | 688 | 56.9k |
| cyankiwi/Qwen3.5-9B-AWQ-BF16-INT4 | Qwen/Qwen3.5-9B | quantized | AWQ | 9.65B | L | apache-2.0 | cyankiwi | 9 | 90.5k |
| z-lab/Qwen3.5-122B-A10B-DFlash | Qwen/Qwen3.5-122B-A10B | finetune | — | 774M | S | apache-2.0 | z-lab | 20 | 87.5k |
| lmstudio-community/Qwen3.5-122B-A10B-GGUF | Qwen/Qwen3.5-122B-A10B | quantized | GGUF | — | — | apache-2.0 | lmstudio-community | 7 | 85.6k |
Get alerts on the Qwen3.5 family
Watch this family
- /feeds/families/Qwen--Qwen3.5.xml(RSS 2.0) · every change to any Qwen3.5 member
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.