Downloads · 30 days
41
39% of all-time downloads
Qwen3.8-27B-imatrix
pugant/Qwen3.8-27B-imatrix
Qwen3.8-27B-imatrix is a machine learning model from pugant. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
imatrix-qwen38.gguf is an importance matrix for the Qwen3.8-27B dense model (GGUF arch qwen35, the same conversion used by unsloth/BF16 GGUFs), in the standard GGUF imatrix format — usable with any llama.cpp via llama…
All-time downloads
104
Public
Repo size
13.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf13.6 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 19, 2026
- Updated
- Sep 4, 2026
- SHA
- bc328fe7
Base models
Model card
From the Hugging Face model README
Importance matrix (imatrix) for Qwen3.8-27B
imatrix-qwen38.gguf is an importance matrix for the Qwen3.8-27B dense model
(GGUF arch qwen35, the same conversion used by unsloth/BF16 GGUFs), in the
standard GGUF imatrix format — usable with any llama.cpp via
llama-quantize --imatrix, no fork required.
It is the matrix used to produce pugant/Qwen3.8-27B-MTP-Q4_0_ROCMFP4_STRIX_LEAN (4.34 BPW effective), where it passed our full quality gate.
Calibration data
Generated from a ~1.7 MB interleaved composite corpus (~131k tokens consumed,
--chunks 256), mixed on purpose so that every chunk window sees all three
components:
| Share | Content | Source |
|---|---|---|
| ~55% | agentic-coding traces (chat format, <think> traces, tool calls) | ProCreations/grug-think-v3-10k — public 10k-conversation dataset (see its card for license terms), originally used to calibrate the grug finetune quants and reused here as the agentic-coding component |
| ~28% | Italian prose | our own documents |
| ~17% | real source code | our own |
Credit where due: the agentic-coding component descends from the grug
calibration work — thanks to the grug community and to
ProCreations for publishing
grug-think-v3-10k. Only aggregate per-block statistics are published here
(sum of squares / counts); no calibration text is included in this repo.
Coverage
- 496/496 quantizable tensors covered (importance-collection gate: PASS).
- Not collectable by design (left at defaults by
llama-quantize): the MTP draft layers (blk.*.nextn),ssm_conv1d,token_embd,output.weight.
Regenerate it
llama-imatrix -m Qwen3.8-27B-BF16.gguf \
-f qwen38-calibration.txt \
-o imatrix-qwen38.gguf \
--chunks 256 --no-ppl --parse-special \
--output-frequency 10 --save-frequency 0 \
-ngl 999
A dense 27B needs the GPU path (-ngl 999); CPU collection would take hours.
Note: llama-imatrix saves silently at the end of the run.
File details
imatrix-qwen38.gguf— 13,642,656 bytes (13.0 MiB)- SHA256:
b5e681d65e726415f899fa8fd4f49e56c3f1d4fd83e3bb8963abce68f881a418
See also
- Quants built with this matrix: pugant/Qwen3.8-27B-MTP-Q4_0_ROCMFP4_STRIX_LEAN (AMD Strix Halo ROCmFP4 preset, includes DFlash2/MTP speculative decoding notes)
- Quantization fork with the ROCmFP4 presets: charlie12345/ROCmFPX
- Calibration dataset: ProCreations/grug-think-v3-10k
Software
- Runtime:
charlie12345/ROCmFPX(fork of llama.cpp) — our experimental build with per-request drafter routing, reasoning budget and spec-boundary cache salvage: full source included in the lab repo underrocmfpx/ - Lab repo (patches, benchmarks, full replication guide):
pugant/strix-nebulosa
The quant built with this matrix and everything linked here is experimental and provided as-is, at your own risk.
- License
- apache-2.0
- Created
- Aug 19, 2026
- Updated
- Sep 4, 2026