Insights DB

pragmaticcs / Qwen-35B-A3B-SignOfFour-Coder-GGUF

Last scanned: Sep 7, 2026 at 11:56 AM UTC

Report an issue

Versions

Version	Commit message	Commit author	Last scanned
e287dd	Update README.md	pragmaticcs	Never scanned
b045f4	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q8_0.gguf	pragmaticcs
5328da	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q6_K.gguf	pragmaticcs
bf768b	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q4_K_M.gguf	pragmaticcs
5502ac	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-BF16-00001-of-00002.gguf	pragmaticcs
a34638	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-APEX-High-Quality.gguf	pragmaticcs
01a1ad	Upload Qwen-35B-A3B-SignOfFour-Coder-Q8_0.gguf (Near-Lossless Reference 8-bit Quantization)	pragmaticcs
3af147	Upload Qwen-35B-A3B-SignOfFour-Coder-Q6_K.gguf (Very High-Quality 6-bit: High-precision MoE routing & Attention)	pragmaticcs
7ada05	Upload Qwen-35B-A3B-SignOfFour-Coder-APEX-High-Quality.gguf (APEX High-Quality: Q5_K_M body + Q8_0 Heads, Embeddings & Shared Experts)	pragmaticcs
9a368e	Upload Qwen-35B-A3B-SignOfFour-Coder-Q5_K_M.gguf (Optimized 5-bit: Q5_K_M body + Q8_0 Embeddings & Shared Experts)	pragmaticcs
c64a93	Upload Qwen-35B-A3B-SignOfFour-Coder-Q4_K_M.gguf (Optimized Fast 4-bit: Q4_K_M body + Q8_0 Embeddings & Shared Experts)	pragmaticcs
92cdcc	Upload Qwen-35B-A3B-SignOfFour-Coder-BF16-00002-of-00002.gguf (Uncompressed BF16 Reference)	pragmaticcs
820647	Upload Qwen-35B-A3B-SignOfFour-Coder-BF16-00001-of-00002.gguf (Uncompressed BF16 Reference)	pragmaticcs
fdf2cc	Update README.md	pragmaticcs
7815aa	Update README.md	pragmaticcs
fb602d	Upload SignOfFour-Q8_0.gguf (Near-Lossless 8-bit Quantization (~37.5 GB))	pragmaticcs
a6ecae	Upload SignOfFour-APEX-High-Quality.gguf (APEX High-Quality: Q5_K_M with Q8_0 Embeddings & Output Head (~25.8 GB))	pragmaticcs
e28ecd	Upload SignOfFour-Q5_K_M.gguf (Standard High-Quality 5-bit Medium Quantization (~25.2 GB))	pragmaticcs
7cf645	Upload SignOfFour-Q4_K_M.gguf (Standard Fast 4-bit Quantization (~20.8 GB))	pragmaticcs
fc8288	Upload SignOfFour-BF16-00002-of-00002.gguf (Uncompressed BF16 Reference)	pragmaticcs

‌
‌
‌
‌
‌
‌
‌
‌
‌
‌

Prisma AIRS detects threats in model files

With Prisma AIRS you can scan models for threats before ML developers download them for use, and apply policies based on your risk tolerance.

Learn more

Found a new threat?

Earn bounties and get recognition for your discoveries by submitting them through Huntr.

Report your finding

Version	Commit message	Commit author	Last scanned
e287dd	Update README.md	pragmaticcs	Never scanned
b045f4	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q8_0.gguf	pragmaticcs
5328da	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q6_K.gguf	pragmaticcs
bf768b	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q4_K_M.gguf	pragmaticcs
5502ac	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-BF16-00001-of-00002.gguf	pragmaticcs
a34638	Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-APEX-High-Quality.gguf	pragmaticcs
01a1ad	Upload Qwen-35B-A3B-SignOfFour-Coder-Q8_0.gguf (Near-Lossless Reference 8-bit Quantization)	pragmaticcs
3af147	Upload Qwen-35B-A3B-SignOfFour-Coder-Q6_K.gguf (Very High-Quality 6-bit: High-precision MoE routing & Attention)	pragmaticcs
7ada05	Upload Qwen-35B-A3B-SignOfFour-Coder-APEX-High-Quality.gguf (APEX High-Quality: Q5_K_M body + Q8_0 Heads, Embeddings & Shared Experts)	pragmaticcs
9a368e	Upload Qwen-35B-A3B-SignOfFour-Coder-Q5_K_M.gguf (Optimized 5-bit: Q5_K_M body + Q8_0 Embeddings & Shared Experts)	pragmaticcs
c64a93	Upload Qwen-35B-A3B-SignOfFour-Coder-Q4_K_M.gguf (Optimized Fast 4-bit: Q4_K_M body + Q8_0 Embeddings & Shared Experts)	pragmaticcs
92cdcc	Upload Qwen-35B-A3B-SignOfFour-Coder-BF16-00002-of-00002.gguf (Uncompressed BF16 Reference)	pragmaticcs
820647	Upload Qwen-35B-A3B-SignOfFour-Coder-BF16-00001-of-00002.gguf (Uncompressed BF16 Reference)	pragmaticcs
fdf2cc	Update README.md	pragmaticcs
7815aa	Update README.md	pragmaticcs
fb602d	Upload SignOfFour-Q8_0.gguf (Near-Lossless 8-bit Quantization (~37.5 GB))	pragmaticcs
a6ecae	Upload SignOfFour-APEX-High-Quality.gguf (APEX High-Quality: Q5_K_M with Q8_0 Embeddings & Output Head (~25.8 GB))	pragmaticcs
e28ecd	Upload SignOfFour-Q5_K_M.gguf (Standard High-Quality 5-bit Medium Quantization (~25.2 GB))	pragmaticcs
7cf645	Upload SignOfFour-Q4_K_M.gguf (Standard Fast 4-bit Quantization (~20.8 GB))	pragmaticcs
fc8288	Upload SignOfFour-BF16-00002-of-00002.gguf (Uncompressed BF16 Reference)	pragmaticcs

Version

Commit message

Commit author

Last scanned

e287dd

Update README.md

pragmaticcs

Never scanned

b045f4

Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q8_0.gguf

pragmaticcs

5328da

Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q6_K.gguf

pragmaticcs

bf768b

Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-Q4_K_M.gguf

pragmaticcs

5502ac

Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-BF16-00001-of-00002.gguf

pragmaticcs

a34638

Fix context_length (262k) and rope.freq_base (10M) for Qwen-35B-A3B-SignOfFour-Coder-APEX-High-Quality.gguf

pragmaticcs

01a1ad

Upload Qwen-35B-A3B-SignOfFour-Coder-Q8_0.gguf (Near-Lossless Reference 8-bit Quantization)

pragmaticcs

3af147

Upload Qwen-35B-A3B-SignOfFour-Coder-Q6_K.gguf (Very High-Quality 6-bit: High-precision MoE routing & Attention)

pragmaticcs

7ada05

Upload Qwen-35B-A3B-SignOfFour-Coder-APEX-High-Quality.gguf (APEX High-Quality: Q5_K_M body + Q8_0 Heads, Embeddings & Shared Experts)

pragmaticcs

9a368e

Upload Qwen-35B-A3B-SignOfFour-Coder-Q5_K_M.gguf (Optimized 5-bit: Q5_K_M body + Q8_0 Embeddings & Shared Experts)

pragmaticcs

c64a93

Upload Qwen-35B-A3B-SignOfFour-Coder-Q4_K_M.gguf (Optimized Fast 4-bit: Q4_K_M body + Q8_0 Embeddings & Shared Experts)

pragmaticcs

92cdcc

Upload Qwen-35B-A3B-SignOfFour-Coder-BF16-00002-of-00002.gguf (Uncompressed BF16 Reference)

pragmaticcs

820647

Upload Qwen-35B-A3B-SignOfFour-Coder-BF16-00001-of-00002.gguf (Uncompressed BF16 Reference)

pragmaticcs

fdf2cc

Update README.md

pragmaticcs

7815aa

Update README.md

pragmaticcs

fb602d

Upload SignOfFour-Q8_0.gguf (Near-Lossless 8-bit Quantization (~37.5 GB))

pragmaticcs

a6ecae

Upload SignOfFour-APEX-High-Quality.gguf (APEX High-Quality: Q5_K_M with Q8_0 Embeddings & Output Head (~25.8 GB))

pragmaticcs

e28ecd

Upload SignOfFour-Q5_K_M.gguf (Standard High-Quality 5-bit Medium Quantization (~25.2 GB))

pragmaticcs

7cf645

Upload SignOfFour-Q4_K_M.gguf (Standard Fast 4-bit Quantization (~20.8 GB))

pragmaticcs

fc8288

Upload SignOfFour-BF16-00002-of-00002.gguf (Uncompressed BF16 Reference)

pragmaticcs

pragmaticcs / Qwen-35B-A3B-SignOfFour-Coder-GGUF

Versions

Prisma AIRS detects threats in model files

Found a new threat?

Products and Services

Company

Popular Links