oQ3e mixed-precision MLX conversion of Nex-AGI's Nex-N2.6, intended for Apple Silicon Macs with 192 GB or more of unified memory, including M2 Ultra Mac Studio systems.
Effective weight storage: 3.69 BPW · 148.35 GB · group size 64.
Nex-N2.6 is a multimodal agentic model based on GLM-5.3-Flash, with approximately 321B parameters. This community conversion retains the full expert set, vision encoder and multi-token-prediction head. No additional training, abliteration or expert pruning was applied.
nex-agi/Nex-N2.6@987472298e7867721576ac49a253a6f5b526013e.0.7.4.dev1 native oQe streaming converter.Detailed conversion and preservation records are in CONVERSION.json.
3.69 effective bits per weight (BPW). The packed quantized matrices alone average 3.163 bits per weight; the effective figure includes their BF16 scales/biases, every unquantized tensor and safetensors headers.
| Component | Weight precision | Original parameters | Stored GB |
|---|---|---|---|
| Routed MoE experts | 3-bit, 4-bit | 311,653,564,416 | 137.254404 |
| Attention projections | 8-bit | 6,171,918,336 | 6.557663 |
| Shared experts | 8-bit | 1,082,130,432 | 1.149764 |
| Dense MLP projections | 8-bit | 452,984,832 | 0.481296 |
| Token embeddings | 8-bit | 634,388,480 | 0.674038 |
| Output head | 8-bit | 634,388,480 | 0.674038 |
| Vision encoder | BF16 | 563,627,008 | 1.127254 |
| Linear-attention convolutions | BF16 | 3,342,336 | 0.006685 |
| Indexer pooling/compression | BF16 | 6,297,600 | 0.012595 |
| Text/MTP normalization | BF16 | 425,216 | 0.000850 |
| MTP fusion projection | BF16 | 33,554,432 | 0.067109 |
| MoE routers/correction biases | FP32 | 50,737,248 | 0.202949 |
| Hyperconnections | FP32 | 35,391,870 | 0.141567 |
| Recurrent decay controls | FP32 | 280,704 | 0.001123 |
| Safetensors headers | — | — | 0.000402 |
| Total | 3.69 effective BPW | 321,323,031,390 | 148.351738 |
Stored GB uses decimal units. Quantized rows include their BF16 affine scales/biases; normalization in this table excludes the vision encoder, whose tensors are all counted in the vision row. Routed/shared expert and attention totals include MTP; the MTP fusion projection is listed separately. No tensors are counted twice.
Calculation: 8 × 148,351,737,770 stored bytes ÷ 321,323,031,390 original scalar parameters = 3.6935 BPW. Affine metadata contributes storage but is not counted as additional original model parameters. Tokenizer/config files, KV cache and runtime workspace are excluded.
| Block | Routed expert matrices | Other quantized matrices | Unquantized tensors | Stored GB |
|---|---|---|---|---|
| Text 0 | — (dense MLP) | 8-bit | BF16, FP32 | 0.310052 |
| Text 1 | — (dense MLP) | 8-bit | BF16, FP32 | 0.310052 |
| Text 2 | — (dense MLP) | 8-bit | BF16, FP32 | 0.310052 |
| Text 3 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 4 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 5 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 6 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 7 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 8 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 9 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 10 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 11 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 12 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 13 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 14 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 15 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 16 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 17 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 18 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 19 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 20 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 21 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 22 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 23 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 24 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 25 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 26 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 27 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 28 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 29 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 30 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 31 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 32 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 33 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 34 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 35 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 36 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 37 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 38 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 39 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 40 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 41 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 42 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| Text 43 | 3-bit | 8-bit | BF16, FP32 | 3.338730 |
| Text 44 | 3-bit | 8-bit | BF16, FP32 | 3.351972 |
| MTP 0 | 4-bit | 8-bit | BF16, FP32 | 4.308687 |
Complete per-module/tensor precision data (CSV) and exact accounting/methodology (JSON) are included. The CSV covers every quantized module and unquantized tensor; quantized module rows include their scales and affine biases.
Use a runtime supporting Nex-N2.6's glm5_next architecture and oQe mixed precision, with the included tokenizer, processor and chat template. The template supports reasoning_effort values low, high and max (default).
Cold loading, text generation, supplied-image recognition and executable coding checks tested on a 256 GB M5 Ultra Mac with oMLX 0.7.4.dev1; MTP decoding active. The generated Dijkstra implementation passed 17 executable checks. Sampled process footprint peaked at 141.81 GiB across the cold load and bounded requests; the largest completed prompt-plus-output was 6,938 tokens.
Intended hardware is a capacity target, not an M2 qualification. M2 Ultra execution, speed and usable context are untested. Runtime, macOS, KV state, generation workspace and the device's Metal/wired-memory budget need headroom beyond the weight files. These are bounded functional checks, not a general quality or full-context benchmark.
Model: Nex-AGI. GLM base: Z.ai. Conversion tooling: oMLX / oQe. Community conversion: Hygaard.
Licensed under Apache-2.0, with the upstream GLM MIT notice retained. See NOTICE for attribution and modification notes.
model-00002-of-00029.safetensors 5.6 GBmodel-00013-of-00029.safetensors 5.3 GBmodel-00022-of-00029.safetensors 5.3 GBmodel-00010-of-00029.safetensors 5.3 GBmodel-00025-of-00029.safetensors 5.3 GBmodel-00015-of-00029.safetensors 5.3 GBmodel-00027-of-00029.safetensors 5.3 GBmodel-00020-of-00029.safetensors 5.3 GBmodel-00017-of-00029.safetensors 5.3 GBmodel-00008-of-00029.safetensors 5.3 GBmodel-00003-of-00029.safetensors 5.3 GBmodel-00005-of-00029.safetensors 5.3 GBmodel-00007-of-00029.safetensors 5.3 GBmodel-00016-of-00029.safetensors 5.3 GBmodel-00019-of-00029.safetensors 5.3 GBmodel-00009-of-00029.safetensors 5.3 GBmodel-00011-of-00029.safetensors 5.3 GBmodel-00012-of-00029.safetensors 5.3 GBmodel-00014-of-00029.safetensors 5.3 GBmodel-00018-of-00029.safetensors 5.3 GBmodel-00023-of-00029.safetensors 5.3 GBmodel-00024-of-00029.safetensors 5.3 GBmodel-00026-of-00029.safetensors 5.3 GBmodel-00021-of-00029.safetensors 5.3 GBmodel-00004-of-00029.safetensors 5.3 GBmodel-00006-of-00029.safetensors 5.3 GBmodel-00028-of-00029.safetensors 5.0 GBmodel-00001-of-00029.safetensors 5.0 GBmodel-00029-of-00029.safetensors 439 MBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Hygaard/Nex-N2.6-oQ3e-mtp ./model-foldernex-agi/Nex-N2.6