Qwen 3 1.7B · Ollama

jstzwhc/Qwen3-TTS

Qwen3-TTS-12Hz-1.7B-Q4_K_M

136 Pulls 1 Tag Updated 1 week ago

Maternion/lfm2

LFM2-8B-A1B is the best on-device MoE in terms of both quality (comparable to 3-4B dense models) and speed (faster than Qwen3-1.7B). Updated LFM2.5-8B-A1B is now available!

tools 8b

2,066 Pulls 4 Tags Updated 5 months ago

reaperdoesntrun/DistilQwen3-1.7B-uncensored

tools thinking

543 Pulls 1 Tag Updated 5 months ago

reaperdoesntrun/Qwen3-Distilled-Coder-1.7B

Coder teacher → STEM distillation → logical inference SFT → quantized. Structured reasoning in ~1.2GB.

tools thinking

291 Pulls 1 Tag Updated 5 months ago

ayushshah/qwen3-1.7b-chat

Preference-aligned conversational assistant based on Qwen3-1.7B-Base. Fine-tuned using UltraChat and optimized with DPO on UltraFeedback, Intel Orca and Capybara

80 Pulls 6 Tags Updated 1 month ago

MadhuryaPasan/qwen3-no-thinking

Qwen3 1.7B (Q8_0) optimized for direct response. Template modified to remove all <think> blocks and force immediate output.

tools thinking

371 Pulls 1 Tag Updated 6 months ago

supere989/vectorcore-qwen-tools

Tool Calling improved version of Qwen3 1.7B where improvements are made to the prompt template data configuration. This version will now consistently perform structured json tool call outputs.

tools

129 Pulls 1 Tag Updated 8 months ago

fervent_mcclintock/Qwen3-1.7B

tools thinking

90 Pulls 1 Tag Updated 6 months ago

clidx/Qwen3-1.7B-Q8_0

tools thinking

399 Pulls 2 Tags Updated 1 year ago

Beanie/Trojan-1-Preview-Qwen3-1.7B

This is an essay writing model extremely effective at evading the ZeroGPT classifier. Performance is not guaranteed on other AI detection tools. This model is for research only, please do not use it for malicious purposes or to cheat on your homework.

tools thinking

150 Pulls 1 Tag Updated 1 year ago

transkatgirl/Qwen3-1.7B-Base

Base model

131 Pulls 1 Tag Updated 1 year ago

xcx0902/Qwen3-1.7B-catgirl

tools

53 Pulls 1 Tag Updated 1 year ago

orcarouter/Qwen3.8-Flash-Next-Uncensored

Qwen3.8-Flash-Next tensor-level abliterated— a latest Qwen4-architecture MoE (~177B total / ~6B active) with vision, reasoning, tool-calling, and 262K context. MLX 4/6/8-bit for Apple Silicon. Research use only.

vision tools thinking

1,376 Pulls 4 Tags Updated 2 days ago

Whittle/Qwen3.8-Whittle-MoE-27B-A17.8B

The architecture is a partition, not a rebuild. All 64 layers keep the parent's attention side untouched: the 3 to 1 hybrid of gated deltanet layers and full attention, 16 attention layers in all, hidden size 5120. The surgery is in the feed forward. Each

145 Pulls 4 Tags Updated 6 days ago

hengwen/Sky-T1-32B-Preview

This is a 32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data. The performance is on par with o1-preview model on both math and coding.

267 Pulls 2 Tags Updated 1 year ago

VladimirGav/qwen3.8-27B-14GB-IQ4

Qwen 3.8 27B (IQ4_XS) - Optimized for 16GB VRAM

474 Pulls 1 Tag Updated 2 days ago

babar_jamali/qwen3-1.7b-nolimits

qwen3-1.7b-nolimits - is ai model that have no limit, no restrictions and fully easy to use and deploy on CPU 8GB RAM

tools thinking

157 Pulls 2 Tags Updated 1 month ago

dna5rm/qwen3.8

Qwen3.8-27B Q4_K_M, default context 131072, tuned for a 32 GB NVIDIA RTX 5090.

vision tools thinking

51 Pulls 1 Tag Updated 1 week ago