Downloads · 30 days
101
10% of all-time downloads
Tess-4-27B-EAGLE3-GGUF
YourHighnessLA/Tess-4-27B-EAGLE3-GGUF
Tess-4-27B-EAGLE3-GGUF is a machine learning model from YourHighnessLA. 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.
GGUF conversions of migtissera/Tess-4-27B-EAGLE3, the EAGLE-3 speculative-decoding draft head for migtissera/Tess-4-27B, for use with mainline llama.cpp's external EAGLE-3 path (--spec-type draft-eagle3).
All-time downloads
998
Public
Repo size
2.3 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.gguf2.3 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026
- SHA
- ba5cb15d
Base models
Model card
From the Hugging Face model README
Tess-4-27B EAGLE-3 Draft — GGUF
GGUF conversions of migtissera/Tess-4-27B-EAGLE3, the EAGLE-3 speculative-decoding draft head for migtissera/Tess-4-27B, for use with mainline llama.cpp's external EAGLE-3 path (--spec-type draft-eagle3).
| File | Size | Notes |
|---|---|---|
Tess-4-27B-EAGLE3-Q4_K_M.gguf | 403 MB | Recommended — acceptance is flat across draft quants, so the smallest draft wins on latency |
Tess-4-27B-EAGLE3-Q8_0.gguf | 629 MB | |
Tess-4-27B-EAGLE3-BF16.gguf | 1.22 GB | Direct converter output |
Usage
llama-server \
-m Tess-4-27B-Q4_K_M.gguf \
--spec-type draft-eagle3 \
--spec-draft-model Tess-4-27B-EAGLE3-Q4_K_M.gguf \
--spec-draft-n-max 2
--spec-draft-n-max 2 is the measured sweet spot on this head — deeper drafting is strictly worse (per-position acceptance decays; rejected drafts waste target verification). Speculative decoding is output-lossless: the target verifies every token, confirmed at benchmark granularity (150-scenario quality suite, within run-to-run noise of no-spec and of a DFlash draft).
Measured performance
Acceptance on this head is modest — it accelerates Tess-4, but a stronger draft beats it where one exists:
| Rig | Config | Acceptance | Throughput |
|---|---|---|---|
| 1× RTX 4090 (Q4_K_M target, ctx 98K) | n_max=2 | 49.1% | ~76–78 code tok/s (vs 50.4 no-spec — 1.55×) |
| 1× RTX 4090 | n_max=4 | 27.4–28.0% (flat across BF16/Q8_0/Q4_K_M draft) | 62–71 tok/s |
| 2× RTX 3090 (club-3090, llama.cpp b9967) | n=2 | 40.8% | 47.5 narr / 61.3 code tok/s |
For context on the same rigs, ~0.70-acceptance heads (DFlash, external MTP) reach 1.9–2×. See noonghunna/club-3090#662 for forensics on this head's acceptance ceiling and #665 / PR #674 for the quality benchmarks behind these numbers. Notably, this head's acceptance is feed-robust: it scores in the same band fed hidden states (vLLM/SGLang, in-graph) or fed tokens (llama.cpp external path).
Conversion recipe
Converted at llama.cpp b9932 (a646006f0); independently reproduced at b9967 — the recipe is version-robust across that span.
# The target dir needs ONLY the base model's config.json + tokenizer files
# (~12 MB download) — no 27B weights required.
python convert_hf_to_gguf.py <Tess-4-27B-EAGLE3-dir> \
--target-model-dir <Tess-4-27B-metadata-dir> # → BF16 GGUF
llama-quantize Tess-4-27B-EAGLE3-BF16.gguf Tess-4-27B-EAGLE3-Q4_K_M.gguf Q4_K_M
llama-quantize Tess-4-27B-EAGLE3-BF16.gguf Tess-4-27B-EAGLE3-Q8_0.gguf Q8_0
The converter reads the target's hidden size (5120) from its config, selects extraction layers [2, 32, 61], and writes the 32K→248K d2t vocab map into the GGUF (eagle3.target_layers / eagle3.target_hidden_size metadata, inspectable with llama-gguf).
License
Apache 2.0, matching the source head and Tess-4-27B. Draft head by Migel Tissera; GGUF conversion and llama.cpp benchmarks as credited above.
- License
- apache-2.0
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026