Interim Labs Qwen3.5-2B · GGUF Q4_K_M
A standalone GGUF Q4_K_M release published by Interim Labs for local text generation. This package derives from Qwen/Qwen3.5-2B. The GGUF weights are redistributed byte-for-byte from the credited conversion source below.
Model series
Part of the Interim Labs Qwen3.5 series: three sizes, each with an original Qwen3.5 variant and a Huihui abliterated variant, in two formats.
| Model | MLX 4-bit | GGUF Q4_K_M |
|---|---|---|
| Qwen3.5 2B | MLX | GGUF |
| Huihui Qwen3.5 2B abliterated | MLX | GGUF |
| Qwen3.5 4B | MLX | GGUF |
| Huihui Qwen3.5 4B abliterated | MLX | GGUF |
| Qwen3.5 9B | MLX | GGUF |
| Huihui Qwen3.5 9B abliterated | MLX | GGUF |
Package details
| Property | Value |
|---|---|
| Parameter class | 2B |
| Format | GGUF |
| Quantization | Q4_K_M |
| Weight file | model.gguf |
| Weight size | 1.40 GB (1,396,198,496 bytes) |
| GGUF architecture | qwen35 |
| Context in GGUF metadata | 262,144 tokens; practical limits depend on runtime and memory |
No tensors were rewritten in this release. The context value in the GGUF metadata is not a claim of tested long-context quality or of memory requirements.
Usage and runtime requirements
Download the package with the Hugging Face CLI:
hf download interimlabs/InterimLabs-Qwen3.5-2B-GGUF-Q4_K_M model.gguf
Load model.gguf in a GGUF runtime with Qwen3.5 (qwen35) support, such as a compatible build of llama.cpp. Q4_K_M support alone is insufficient if the runtime does not support the model architecture. Choose context and GPU offload settings for your available memory. Compatibility across applications has not been comprehensively verified.
Sources and conversion
- GGUF source: bartowski/Qwen_Qwen3.5-2B-GGUF at
7d26695454df6de5fbcce2e58681e62dae06ce43. - Source weight file:
Qwen_Qwen3.5-2B-Q4_K_M.gguf. - Reference upstream: Qwen/Qwen3.5-2B at
15852e8c16360a2fea060d615a32b45270f8a8fc.
The conversion source does not establish the exact upstream revision used for its conversion. The reference revision above documents the inspected upstream snapshot, not a verified conversion lineage.
See provenance.json for source and package metadata.
Weight-file SHA-256:
57a1085840f497d764a7fc5d346922dbde961efb54cc792ea81d694fd846a1d8
Evaluation and limitations
This release does not include a comprehensive benchmark of the packaged model. No writing-quality, reliability, or performance improvement over the credited source is claimed.
License and credits
Distributed under Apache-2.0. Credit belongs to the Qwen team and the conversion authors linked above. Interim Labs publishes this package and its documentation. See the linked upstream cards for the original model details and limitations.