Filter by type:
Filter by tags:
pocket-35b
POCKET-35B is an Apache-2.0 Qwen3.5-family mixture-of-experts model from
FINAL-Bench/VIDRAFT, derived from Darwin-36B-Opus and packaged for stock
llama.cpp. This entry uses the quality-oriented Q4_K_M GGUF quantization.
Repository: localaiLicense: apache-2.0
pocket-35b-q2
POCKET-35B is an Apache-2.0 Qwen3.5-family mixture-of-experts model from
FINAL-Bench/VIDRAFT, derived from Darwin-36B-Opus and packaged for stock
llama.cpp. This entry uses the smaller Q2_K GGUF quantization.
Repository: localaiLicense: apache-2.0
pocket-35b-iq1
POCKET-35B is an Apache-2.0 Qwen3.5-family mixture-of-experts model from
FINAL-Bench/VIDRAFT, derived from Darwin-36B-Opus and packaged for stock
llama.cpp. This entry uses the most compact IQ1_M GGUF quantization.
Repository: localaiLicense: apache-2.0
pocket-26b
POCKET-26B is an Apache-2.0 Gemma 4 26B-A4B mixture-of-experts model from
FINAL-Bench/VIDRAFT, tuned for Korean and packaged for stock llama.cpp.
This entry uses the quality-oriented Q4_K_M GGUF quantization.
Repository: localaiLicense: apache-2.0
pocket-26b-q2
POCKET-26B is an Apache-2.0 Gemma 4 26B-A4B mixture-of-experts model from
FINAL-Bench/VIDRAFT, tuned for Korean and packaged for stock llama.cpp.
This entry uses the smaller Q2_K GGUF quantization.
Repository: localaiLicense: apache-2.0
mellum2-12b-a2.5b-instruct
Mellum2-12B-A2.5B-Instruct is an Apache-2.0 mixture-of-experts model from
JetBrains with 12 billion total parameters, 2.5 billion activated per token,
and a 131,072-token context window.
This entry uses the Q4_K_M GGUF quantization.
Repository: localaiLicense: apache-2.0
mellum2-12b-a2.5b-instruct-q8
Mellum2-12B-A2.5B-Instruct is an Apache-2.0 mixture-of-experts model from
JetBrains with 12 billion total parameters, 2.5 billion activated per token,
and a 131,072-token context window.
This entry uses the higher-quality Q8_0 GGUF quantization.
Repository: localaiLicense: apache-2.0
bonsai-8b-1bit
Bonsai 8B (PrismML) is an end-to-end 1-bit language model built on the Qwen3-8B dense
architecture (GQA, SwiGLU, RoPE, RMSNorm, 36 layers, 65,536 context). Every weight is a
single sign bit (`-scale` / `+scale`) with one FP16 scale per group of 128 weights, for
an effective 1.125 bits/weight and a ~1.15 GB footprint (14.2x smaller than FP16) while
matching full-precision 8B instruct models at ~70.5 average across 6 benchmark
categories.
The Q1_0 quantization is only decodable by the PrismML llama.cpp fork, so this entry
runs on LocalAI's `bonsai` backend (that fork), not the stock `llama-cpp` backend.
License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-8b
Ternary Bonsai 8B (PrismML) is a 1.58-bit ternary language model on the Qwen3-8B dense
architecture. Each weight takes a value from {-1, 0, +1} with one shared FP16 scale per
group of 128 weights (GGUF Q2_0, ~2.18 GB deployed, 7.5x smaller than FP16). The extra
zero state recovers more of the full-precision model than the 1-bit build: it ranks 2nd
among compared 6-9B models at 75.5 average despite being ~1/8th their size.
Q2_0 is the recommended, ternary-lossless variant. The Q2_0 kernels are only in the
PrismML llama.cpp fork, so this runs on LocalAI's `bonsai` backend. License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-8b-q2-g64
Ternary Bonsai 8B (PrismML), GGUF Q2_0 with group-64 packing (each FP16 scale shared
across 64 weights instead of 128). Slightly larger (~2.31 GB) but matches llama.cpp's
native 64-value Q2_0 block layout. Runs on LocalAI's `bonsai` backend. License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-8b-pq2
Ternary Bonsai 8B (PrismML), GGUF PQ2_0 (packed Q2_0) ternary variant (~2.18 GB).
Same {-1, 0, +1} weight alphabet as Q2_0. Runs on LocalAI's `bonsai` backend.
License: Apache 2.0.
Repository: localaiLicense: apache-2.0
bonsai-27b-1bit
Bonsai 27B (PrismML) is a full 27B-class reasoning model in end-to-end 1-bit weights,
derived from the Qwen3.6-27B hybrid-attention backbone (~75% linear attention, 262K
context). At a true 1.125 bits/weight it deploys in ~3.9 GB (~14.2x smaller than FP16)
while retaining 89.5% of FP16 intelligence across 15 thinking-mode benchmarks (math
91.66, coding 81.88). Ships an optional 4-bit vision tower (mmproj) for image input,
included here.
The Q1_0_g128 weights and hybrid-attention kernels are only in the PrismML llama.cpp
fork, so this runs on LocalAI's `bonsai` backend. A GPU is recommended. License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-27b
Ternary Bonsai 27B (PrismML) is the quality-oriented operating point of the Bonsai 27B
family: full 27B-class reasoning in ternary {-1, 0, +1} weights on the Qwen3.6-27B
hybrid-attention backbone (262K context). At a true 1.71 bits/weight it deploys in
~7.2 GB (GGUF Q2_0_g128) and retains 95% of FP16 intelligence (80.49 average across 15
thinking-mode benchmarks) - a higher score than a conventional IQ2_XXS build at less
than two-thirds its footprint. Ships an optional 4-bit vision tower (mmproj), included.
The Q2_0 weights and hybrid-attention kernels are only in the PrismML llama.cpp fork,
so this runs on LocalAI's `bonsai` backend. A GPU is recommended. License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-27b-pq2
Ternary Bonsai 27B (PrismML), GGUF PQ2_0 (packed Q2_0) ternary variant (~7.17 GB) with
the 4-bit vision tower (mmproj) included. Runs on LocalAI's `bonsai` backend.
License: Apache 2.0.
Repository: localaiLicense: apache-2.0
ternary-bonsai-27b-q2-g64
Ternary Bonsai 27B (PrismML), GGUF Q2_0 with group-64 packing (~7.59 GB), matching
llama.cpp's native 64-value Q2_0 block layout, with the 4-bit vision tower (mmproj)
included. Runs on LocalAI's `bonsai` backend. License: Apache 2.0.
Repository: localaiLicense: apache-2.0
qwen3-4b-dflash
Qwen3-4B paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend. This is the canonical DFlash pairing documented upstream (`z-lab/Qwen3-4B-DFlash` + `Qwen/Qwen3-4B`).
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The Q4_K_M file carries the full Qwen3-4B target; the ~0.5 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0 (Qwen3-4B target) / MIT (z-lab DFlash drafter).
Repository: localaiLicense: apache-2.0
qwen3.5-4b-dflash
Qwen3.5-4B paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend.
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The Q4_K_M file carries the full Qwen3.5-4B target; the ~0.6 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0 (Qwen3.5-4B target) / MIT (z-lab DFlash drafter).
Repository: localaiLicense: apache-2.0
qwen3.5-9b-dflash
Qwen3.5-9B paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend.
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The Q4_K_M file carries the full Qwen3.5-9B target; the ~1 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0 (Qwen3.5-9B target) / MIT (z-lab DFlash drafter).
Repository: localaiLicense: apache-2.0
qwen3.6-27b-dflash
Qwen3.6-27B (dense) paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend. DFlash gives its largest speedups on dense targets like this one.
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The Q4_K_M file carries the full Qwen3.6-27B target; the ~1.8 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0.
Repository: localaiLicense: apache-2.0
qwen3.6-35b-a3b-dflash
Qwen3.6-35B-A3B (Mixture-of-Experts, ~3B active per token) paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend. DFlash speedups on MoE targets are smaller than on dense models, but still useful.
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The UD-Q4_K_M file carries the full Qwen3.6-35B-A3B target; the ~0.4 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0.
Repository: localaiLicense: apache-2.0
gemma-4-26b-a4b-it
Google Gemma 4 26B-A4B-IT is an open-source multimodal Mixture-of-Experts model with 26B total parameters and 4B active parameters. It handles text and image input, generating text output, with a 256K context window and support for 140+ languages. The MoE architecture provides strong performance with efficient inference. Well-suited for question answering, summarization, reasoning, and image understanding tasks.
Repository: localaiLicense: apache-2.0
Page 1