README
Qwen3.8 Flash Next for DwarfStar
Self-contained GGUFs for DwarfStar, with
original BF16 n-grams read directly from disk. Keep the file on a local SSD.
No n-gram sidecar is needed. MTP weights are included; enable them with --mtp.
Requires DwarfStar's native BF16 n-gram reader. Older versions expecting
--ple cannot load these files.
| File | File size | Main/MTP weights |
|---|---|---|
| Qwen3.8-Flash-Next-Q2.gguf | 137.10 GiB | 41.73 GiB |
| Qwen3.8-Flash-Next-Q4.gguf | 165.11 GiB | 69.74 GiB |
Each file contains the same 95.37 GiB BF16 n-gram table. It is not made resident or quantized. Context and runtime buffers require additional RAM.
The main/MTP tensor bytes come unchanged from Ivan Fioravanti's Q2 and Q4 releases. Q2 has imatrix-calibrated IQ2_XXS gate/up and Q2_K down routed experts, with the down rows padded from 640 to 768 inputs. Q4 has calibrated Q4_K gate/up and MXFP4 down. Other tensor formats and MTP weights are unchanged.
The n-grams are copied byte-for-byte from Qwen's original checkpoint at
de4b8e4d43b917e7706784d8bb445c9af86a3540, including its padding rows.
The packer checks the original hash constants and verifies every copied
payload. These are quantized language-model weights, not lossless copies
of the whole original model.
Original model: Qwen. Quantized main/MTP releases: Ivan Fioravanti.
Native n-gram packaging and disk-only integration: Salvatore Sanfilippo / DwarfStar.
The original Qwen Community License is included as LICENSE.
README
Qwen3.8 Flash Next for DwarfStar
Self-contained GGUFs for DwarfStar, with
original BF16 n-grams read directly from disk. Keep the file on a local SSD.
No n-gram sidecar is needed. MTP weights are included; enable them with --mtp.
Requires DwarfStar's native BF16 n-gram reader. Older versions expecting
--ple cannot load these files.
| File | File size | Main/MTP weights |
|---|---|---|
| Qwen3.8-Flash-Next-Q2.gguf | 137.10 GiB | 41.73 GiB |
| Qwen3.8-Flash-Next-Q4.gguf | 165.11 GiB | 69.74 GiB |
Each file contains the same 95.37 GiB BF16 n-gram table. It is not made resident or quantized. Context and runtime buffers require additional RAM.
The main/MTP tensor bytes come unchanged from Ivan Fioravanti's Q2 and Q4 releases. Q2 has imatrix-calibrated IQ2_XXS gate/up and Q2_K down routed experts, with the down rows padded from 640 to 768 inputs. Q4 has calibrated Q4_K gate/up and MXFP4 down. Other tensor formats and MTP weights are unchanged.
The n-grams are copied byte-for-byte from Qwen's original checkpoint at
de4b8e4d43b917e7706784d8bb445c9af86a3540, including its padding rows.
The packer checks the original hash constants and verifies every copied
payload. These are quantized language-model weights, not lossless copies
of the whole original model.
Original model: Qwen. Quantized main/MTP releases: Ivan Fioravanti.
Native n-gram packaging and disk-only integration: Salvatore Sanfilippo / DwarfStar.
The original Qwen Community License is included as LICENSE.