Filter by type:
Filter by tags:
deepseek-v4.1-flash-1017
# DeepSeek-V4.1-Flash-1017
Technical Report 👁️
## Introduction
**DeepSeek-V4.1-Flash-1017** is a minor update to **DeepSeek-V4.1-Flash**, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses.
*† denotes the text-only subset of HLE. We use the Claude Code harness for Terminal-Bench 4.0 and the Mini-SWE-V2 harness for DeepSWE v1.1.*
## Prompt Encoding
This release does not include a Jinja-format chat template. The `encoding` folder contains a self-contained Python reference implementation (`encoding.py`) with test cases for multi-turn conversations, tool calling, thinking mode, numeric reasoning effort, mid-conversation system messages, and interleaved image content.
...
Repository: localaiLicense: mit
qwen3.8-27b-imatrix-nvfp4-mtp
Qwen3.8-27B in cdiamond's iMatrix-calibrated mixed-precision NVFP4
build. Selected attention and feed-forward tensors retain higher
precision. Includes the F16 vision projector and enables the embedded
MTP draft head with one draft token per step.
Repository: localaiLicense: apache-2.0
swift-qwen3.8-27b
Swift-Qwen3.8-27B is UkisAI's reasoning-efficient fine-tune of Qwen3.8-27B.
The publisher reports 58.3% fewer thinking tokens with less than 1% quality loss.
This Q4_K_M GGUF includes the F16 vision projector and enables MTP speculative decoding.
The weights use the Swift Open License v1.0.
Repository: localaiLicense: swift-open-license-1.0
thinkingcap-qwen3.8-27b
ThinkingCap is a 27B Qwen3.8 fine-tune trained to reduce reasoning tokens, with text and image input.
This Q4_K_M GGUF build uses llama.cpp, the embedded chat template, and the F16 vision projector.
Licensed under PolyForm Small Business 1.0.0 with the publisher's personal-use grant; see the model license for permitted use.
Repository: localaiLicense: polyform-small-business-1.0.0
thinkingcap-qwen3.8-27b-q8
ThinkingCap is a 27B Qwen3.8 fine-tune trained to reduce reasoning tokens, with text and image input.
This Q8_0 GGUF build uses llama.cpp, the embedded chat template, and the F16 vision projector.
Licensed under PolyForm Small Business 1.0.0 with the publisher's personal-use grant; see the model license for permitted use.
Repository: localaiLicense: polyform-small-business-1.0.0
qwen3.8-27b-turbo-fable-cold-fusion-735-882-heretic-uncensored-neo-coder-max-mtp
RELEASE #1 GGUFS [including detailed notes, how to use, benches and much more]:
https://huggingface.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU (release #1, others pending...)
( repo has 10+ other versions (and 3 branches) noted below that EXCEED the performance of all QWEN 27B models, including fine tunes. )
First, special thanks to Nightmedia for working on the first three stages prior to heretic'ing/post staging and benching everything (3 sections below).
A number of my finetunes - both released and non-released - were used here as well as some third parties. Full details will be disclosed upon final release as the project shores up.
THREE example generations [snippets] from STAGE1-PART2, STAGE1b-PART2 and STAGE2-rplus2 at the bottom of the page.
Release(s) will be GGUFS first (linked here directly) then source code shortly thereafter [now released/open].
Some additional work and/ spawning of new branches from branch(es) below is still going on.
NEW: Branch 3 added, see below.
COMPLETED AND PENDING RELEASES:
...
Repository: localaiLicense: apache-2.0
apodex-1.1-mini-q4
Apodex-1.1-mini is an Apache-2.0 Qwen3.5 mixture-of-experts model for
long-horizon research, data analysis, coding, file work, and tool use. It
activates about 3B of its 35.95B parameters per token and supports text and
image input with a context window of 262K tokens.
This default entry uses the recommended Q4_K_M GGUF and F16 vision
projector. An MTP-enabled build and a higher-quality Q8_0 model are
available as variants.
Repository: localaiLicense: apache-2.0
apodex-1.1-mini-q4-mtp
Apodex-1.1-mini with MTP speculative decoding enabled on the recommended
Q4_K_M GGUF. The model carries its native MTP head, so it needs no separate
draft model. The F16 vision projector supports multimodal prompts.
Repository: localaiLicense: apache-2.0
apodex-1.1-mini-q8
Apodex-1.1-mini in the higher-quality Q8_0 GGUF format, with the shared F16
vision projector for multimodal prompts.
Repository: localaiLicense: apache-2.0
llm-jp-4-33b-thinking-q4
LLM-jp-4-33B-thinking is an Apache-2.0 Japanese and English reasoning
model from Japan's National Institute of Informatics. Its dense Llama
architecture has 33 billion parameters and a 65K-token context window.
The model was aligned with supervised fine-tuning and DPO for multi-turn
conversation and instruction following.
This default entry uses the 20.2 GB Q4_K_M GGUF. The official 66.4 GB
BF16 weights are available as a higher-fidelity variant.
Repository: localaiLicense: apache-2.0
llm-jp-4-33b-thinking-bf16
LLM-jp-4-33B-thinking in the official 66.4 GB BF16 GGUF format. This
variant preserves the original model precision for hosts with enough
memory.
Repository: localaiLicense: apache-2.0
qwen3.8-flash-next-q4
Qwen3.8-Flash-Next is Qwen's 125B-parameter, 6B-active experimental
vision-language mixture-of-experts model. It targets agentic coding,
reasoning, tool use, and long-context workloads with a native 262K-token
context window.
This default entry uses Unsloth's UD-Q4_K_XL GGUF and BF16 vision
projector. Linked variants offer Q8_0 and AtomicChat's smaller IQ4_XS
and Q4_K_M builds with a separate n-gram table shard.
Repository: localaiLicense: other
qwen3.8-flash-next-q8
Qwen3.8-Flash-Next in the higher-quality Q8_0 GGUF format, with the shared
BF16 vision projector. This build preserves more model quality but needs
more memory than the default Q4 variant.
Repository: localaiLicense: other
qwen3.8-flash-next-turbo-brilliance-iq3-s
DavidAU's Turbo Brilliance build of Qwen3.8 Flash Next uses GSQ-RCO
IQ3_S mixed quantization and the publisher's embedded chat template.
Includes both GGUF shards and the BF16 vision projector for text chat
and image input, with a 32K default context. See the model card for
the publisher's reasoning and instruction modes.
Repository: localaiLicense: other
qwen3.8-flash-next-gsq-rco-q2-0
Qwen3.8 Flash Next with ISTA DASLab's GSQ-RCO Q2_0 mixed quantization.
Includes both GGUF shards (transformer weights and n-gram embeddings)
and the BF16 vision projector for text chat and image input.
Uses llama.cpp with the embedded chat template and a 32K context.
Repository: localaiLicense: other
qwen3.8-flash-next-gsq-rco-iq2-xs
Qwen3.8 Flash Next with ISTA DASLab's GSQ-RCO IQ2_XS mixed quantization.
Includes both GGUF shards (transformer weights and n-gram embeddings)
and the BF16 vision projector for text chat and image input.
Uses llama.cpp with the embedded chat template and a 32K context.
Repository: localaiLicense: other
qwen3.8-flash-next-gsq-rco-iq3-xxs
Qwen3.8 Flash Next with ISTA DASLab's GSQ-RCO IQ3_XXS mixed quantization.
Includes both GGUF shards (transformer weights and n-gram embeddings)
and the BF16 vision projector for text chat and image input.
Uses llama.cpp with the embedded chat template and a 32K context.
Repository: localaiLicense: other
qwen3.8-flash-next-atomic-iq4
Qwen3.8 Flash Next in AtomicChat's AD-3.84bpw IQ4_XS M64 GGUF
build, with the F16 vision projector. The n-gram table occupies a
separate shard. This entry enables memory mapping and disables llama.cpp
automatic parameter fitting as required by the publisher.
Repository: localaiLicense: other
qwen3.8-flash-next-atomic-q4
Qwen3.8 Flash Next in AtomicChat's AD-4.27bpw Q4_K_M M64 GGUF
build, with the F16 vision projector. The n-gram table occupies a
separate shard. This entry enables memory mapping and disables llama.cpp
automatic parameter fitting as required by the publisher.
Repository: localaiLicense: other
ling-3.0-tiny-q4
Ling-3.0-tiny is InclusionAI's MIT-licensed hybrid reasoning MoE model
with 7.9B total parameters and 1.3B active parameters per token. It
targets reasoning, coding, instruction following, and agentic tasks with
a native 131K-token context window.
This default entry uses the Q4_K_M GGUF. A higher-quality Q8_0 model is
available as a variant.
Repository: localaiLicense: mit
ling-3.0-tiny-q8
Ling-3.0-tiny in the higher-quality Q8_0 GGUF format. This variant
preserves more model fidelity for hosts with enough memory.
Repository: localaiLicense: mit
Page 1