Downloads · 30 days
280
3% of all-time downloads
vinpix/Ternary-Bonsai-27B-Stock-MTP-GGUF
Ternary-Bonsai-27B-Stock-MTP-GGUF is a text generation model from vinpix. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as apache-2.0.
One target, one embedded NextN predictor, one deployment artifact per representation.
Downloads · 30 days
280
3% of all-time downloads
All-time downloads
10.9K
Public
Repo size
19.3 GB
Likes
9
Public
Click a slice to open those files.
.gguf19.3 GB · 100%
From the Hugging Face model README
One target, one embedded NextN predictor, one deployment artifact per representation.
qwen35 · 64 target blocks · 1 embedded NextN block · 866 tensors · Apache-2.0
This repository publishes two self-contained GGUF representations of the same logical model graph:
TQ2_0 — primary, native ternary representationQ2_K — compatibility-oriented standard representationEach file contains both the 27B-class target and its embedded Qwen-style
NextN/MTP predictor. There is no sidecar drafter, no second model identity and
no --model-draft lifecycle.
The two files preserve the same logical tensor set, names, shapes and ordering. They do not claim bit-identical dequantized values, logits or generated text: the storage and dequantization contracts are different.
| Priority | Representation | File | Exact size | SHA-256 |
|---|---|---|---|---|
| 1 | Native TQ2_0 | Ternary-Bonsai-27B-MTP-TQ2_0.gguf | 8,785,215,776 bytes / 8.18 GiB | 480c695b0de5b78b720d7f500eb3e1650359d0ac8e18c29b231a14b2d9c9bf20 |
| 2 | Standard Q2_K | Ternary-Bonsai-27B-MTP-Q2_K.gguf | 10,491,466,016 bytes / 9.77 GiB | 850b4f4041c7d73e4442f23b1c70464f68fb76bf8717bc13ada1562680684410 |
TQ2_0 — primary artifactChoose this file when the target runtime supports the native TQ2_0 tensor
type.
TQ2_0;qwen35, draft-mtp and TQ2_0.Q2_K — compatibility artifactChoose this file when standard Q2_K tensor support is preferable to native
TQ2_0 support.
Q2_K;Q2_K remain Q2_K;Q2_K tensors;Q2_K carries its own
block metadata;qwen35 architecture and embedded
draft-mtp execution.The Q2_K file is a deterministic representation transform, not a generic
calibration-based post-training quantization pass.
| Requirement | Recommended file |
|---|---|
| Minimum repository artifact size | Ternary-Bonsai-27B-MTP-TQ2_0.gguf |
| Native ternary execution | Ternary-Bonsai-27B-MTP-TQ2_0.gguf |
Runtime already supports TQ2_0 | Ternary-Bonsai-27B-MTP-TQ2_0.gguf |
Prefer standard Q2_K tensor storage | Ternary-Bonsai-27B-MTP-Q2_K.gguf |
Runtime lacks TQ2_0 but supports Q2_K | Ternary-Bonsai-27B-MTP-Q2_K.gguf |
| Need embedded MTP without a sidecar drafter | either file |
| Need architecture-independent output equivalence between representations | neither; no such claim is made |
self-contained GGUF
│
├── qwen35 target
│ ├── target token embedding
│ ├── 64 transformer blocks
│ ├── final normalization
│ └── target output path
│
└── embedded MTP / NextN path
├── dedicated MTP token embedding
├── 1 Qwen-style NextN predictor block
├── MTP normalization
└── MTP output path
The ordinary target path and the speculative path resolve from the same file and the same target identity.
| Deployment property | External drafter | This repository |
|---|---|---|
| Target files | 1 | 1 |
| Drafter files | 1 | 0 |
| Runtime model identities | 2 | 1 |
| Independent target/drafter version skew | possible | structurally removed |
| Separate drafter checksum | required | not applicable |
--model-draft / -md | required | not used |
Embedded draft-mtp path | not intrinsic | yes |
The files contain the same 866 logical tensors. The difference is the storage type of the 480 ternary tensors.
TQ2_0TQ2_0 480
Q2_K 17
F32 359
Q4_K 1
Q5_K 6
Q6_K 3
-------------
total 866
Q2_KQ2_K 497
F32 359
Q4_K 1
Q5_K 6
Q6_K 3
-------------
total 866
The compatibility artifact converts each native ternary block into an ordinary
84-byte Q2_K block:
16 bytes scale/min metadata
64 bytes packed 2-bit symbols
2 bytes fp16 d
2 bytes fp16 dmin
---------
84 bytes total
For the 480 converted tensors, the transform follows this contract:
packed Q2_K symbols = packed native ternary symbols
group metadata =
0x00 when all 16 symbols in the logical group are the center symbol
0xFF otherwise
Q2_K d = fp16(fp32(native_scale) / 15)
Q2_K dmin = fp16(fp32(native_scale) / 15)
Consequences:
Q2_K block layout;TQ2_0 dequantization;This distinction is intentional: the Q2_K variant is a compatibility
representation of the ternary code field, not an assertion that the two
dequantizers are interchangeable.
Use a llama.cpp revision that supports:
qwen35 architecture;draft-mtp path;TQ2_0 for the primary artifact, or standard Q2_K for the compatibility
artifact.The Q2_K variant removes the native tensor-type requirement. It does not
remove the architecture or MTP-runtime requirements.
Runtime option names can change across llama.cpp revisions. Confirm the
available flags with:
llama-cli --help | grep -E 'draft-mtp|spec-draft|model-draft'
TQ2_0hf download vinpix/Ternary-Bonsai-27B-Stock-MTP-GGUF \
Ternary-Bonsai-27B-MTP-TQ2_0.gguf \
SHA256SUMS \
--local-dir .
Q2_Khf download vinpix/Ternary-Bonsai-27B-Stock-MTP-GGUF \
Ternary-Bonsai-27B-MTP-Q2_K.gguf \
SHA256SUMS \
--local-dir .
Verify either or both downloaded artifacts:
sha256sum -c SHA256SUMS --ignore-missing
Select one artifact:
MODEL="Ternary-Bonsai-27B-MTP-TQ2_0.gguf"
# or:
# MODEL="Ternary-Bonsai-27B-MTP-Q2_K.gguf"
llama-cli \
-m "$MODEL" \
-p "Derive a cost model for speculative decoding." \
-n 256
llama-cli \
-m "$MODEL" \
--spec-type draft-mtp \
--spec-draft-n-max 2 \
-p "Derive a cost model for speculative decoding." \
-n 256
There is deliberately no -md / --model-draft argument.
llama-server \
-m "$MODEL" \
--spec-type draft-mtp \
--spec-draft-n-max 2 \
--host 127.0.0.1 \
--port 8080
Embedded MTP is beneficial only when the accepted speculative work amortizes predictor and verification cost:
(C_draft + C_verify) / E[committed draft tokens] < C_target-step
Acceptance rate is an intermediate statistic, not the optimization objective. The relevant endpoint is end-to-end committed-token throughput under a fixed workload and configuration.
A minimal controlled comparison is:
A. ordinary target decode
B. draft-mtp with n_max = 1
C. draft-mtp with n_max = 2
Hold constant:
Report separately:
Do not compare the native and compatibility representations while attributing the entire difference to MTP: that changes two independent variables at once.
No hardware-independent speedup claim is made by this repository.
The public claims below are properties of the files and metadata, not of a specific workstation.
| Check | Native TQ2_0 | Standard Q2_K |
|---|---|---|
| Exact byte length recorded | pass | pass |
| SHA-256 recorded | pass | pass |
| GGUF V3 parse | pass | pass |
Architecture metadata: qwen35 | pass | pass |
| Logical tensor count: 866 | pass | pass |
| Target depth: 64 blocks | pass | pass |
| Embedded NextN depth: 1 block | pass | pass |
| Tensor-name, shape and order inventory | pass | pass |
| Expected type histogram | pass | pass |
| Converted native tensors | not applicable | 480 / 480 |
| Public metadata privacy scan | pass | pass |
| Hub object size and content hash verification | pass | verified at publication |
The model card intentionally publishes no workstation-specific throughput, device name, driver name, local path, hostname or private build log.
The checksum is the authoritative artifact identity; the filename is a human-readable label.
| File | SHA-256 |
|---|---|
Ternary-Bonsai-27B-MTP-TQ2_0.gguf | 480c695b0de5b78b720d7f500eb3e1650359d0ac8e18c29b231a14b2d9c9bf20 |
Ternary-Bonsai-27B-MTP-Q2_K.gguf | 850b4f4041c7d73e4442f23b1c70464f68fb76bf8717bc13ada1562680684410 |
Verify explicitly:
printf '%s %s\n' \
'480c695b0de5b78b720d7f500eb3e1650359d0ac8e18c29b231a14b2d9c9bf20' \
'Ternary-Bonsai-27B-MTP-TQ2_0.gguf' \
| sha256sum -c -
printf '%s %s\n' \
'850b4f4041c7d73e4442f23b1c70464f68fb76bf8717bc13ada1562680684410' \
'Ternary-Bonsai-27B-MTP-Q2_K.gguf' \
| sha256sum -c -
This is a model-engineering artifact. It is not a new pretraining run and not an instruction fine-tune.
The final graph combines:
qwen35 GGUF graph;| Role | Immutable source | Revision | Source SHA-256 |
|---|---|---|---|
| Ternary target trunk | prism-ml/Ternary-Bonsai-27B-gguf | 3f8cc399dde45ac0475d023634974407af34907c | f659ca3dd7e28ada5d8b5f3637862d0d51ef433bde032ec4c8990ed27c91a385 |
| MTP donor package | lym00/Qwen3.6-27B-MTP-ONLY-GGUF | 03b35db648da71e23ecfb239f70661e069b16054 | 97697fc5278d4bfd0afaa733ba28c4338cb0396b98d5f5acb781e515f72b52c0 |
The donor package identifies Qwen3.6-derived MTP material but does not pin a separate underlying Qwen source revision. This card does not invent one.
The predictor was grafted from a compatible donor. It was not jointly trained with the final ternary target.
See NOTICE for attribution and LICENSE for terms.
This repository claims:
Q2_K artifact;Q2_K storage for the compatibility representation.This repository does not claim:
TQ2_0 and Q2_K;lym00 or llama.cpp.Q2_K compatibility representation is larger than native TQ2_0.Repository artifacts are distributed under Apache-2.0, subject to the included
LICENSE and NOTICE files and the terms of the source artifacts.
This independent release is not endorsed by Prism ML, Qwen, Alibaba Cloud,
lym00 or the llama.cpp project.
@misc{vinpix2026ternarybonsai27bembeddedmtp,
title = {Ternary Bonsai 27B with Embedded MTP: Native TQ2_0 and Standard Q2_K GGUF},
author = {vinpix},
year = {2026},
url = {https://huggingface.co/vinpix/Ternary-Bonsai-27B-Stock-MTP-GGUF}
}
Primary representation: native TQ2_0
Compatibility representation: standard Q2_K
Deployment boundary: one GGUF, one checksum, no sidecar drafter