truthcoder commited on
Commit
2eab4c0
·
verified ·
1 Parent(s): af8d2fb

TC Mini 4B GGUF: Q4_K_M, Q8_0, F16

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ TC-Mini-4B-F16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ TC-Mini-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
38
+ TC-Mini-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mlabonne/Qwen3-4B-abliterated
4
+ base_model_relation: quantized
5
+ pipeline_tag: text-generation
6
+ tags: [gguf, llama.cpp, ollama, lm-studio, on-device, offline, private, abliterated, uncensored, qwen3]
7
+ ---
8
+ # TC Mini 4B — GGUF (Ollama · LM Studio · llama.cpp)
9
+
10
+ Private AI that runs fully on your own computer. Best for: desktops and laptops (GPU or Apple Silicon).
11
+ Part of **TC Mini**: also runs in your phone's browser — https://truthprotectors.github.io/TC-Mini/app/ · code https://github.com/truthprotectors/TC-Mini · all sizes https://huggingface.co/truthcoder/TC-Mini
12
+
13
+ ```bash
14
+ ollama run hf.co/truthcoder/TC-Mini-4B-GGUF:Q4_K_M
15
+ llama-cli -hf truthcoder/TC-Mini-4B-GGUF:Q4_K_M
16
+ ```
17
+ LM Studio: search `truthcoder/TC-Mini-4B-GGUF`. Add `/no_think` to a message to skip the thinking step.
18
+
19
+ | File | Quant | Size |
20
+ |---|---|---|
21
+ | `TC-Mini-4B-F16.gguf` | F16 | 8.05 GB |
22
+ | `TC-Mini-4B-Q4_K_M.gguf` | Q4_K_M | 2.50 GB |
23
+ | `TC-Mini-4B-Q8_0.gguf` | Q8_0 | 4.28 GB |
24
+
25
+ Q4_K_M = smallest, recommended · Q8_0 = near-lossless · F16 = full precision (for re-quantizing).
26
+
27
+ **Lineage (honest):** [mlabonne/Qwen3-4B-abliterated](https://huggingface.co/mlabonne/Qwen3-4B-abliterated) (Qwen3 with refusal directions removed by mlabonne), converted with llama.cpp `convert_hf_to_gguf.py` and quantized with `llama-quantize`. Not fine-tuned by us. 0/8 refusals on our 8-prompt probe (browser build of the same weights). You are responsible for how you use it.
28
+
29
+ SHA-256:
30
+ ```
31
+ 7e91d02b780f1b071bc062d37d659a3c9ac6b90407b80ad8bfd15ac01b839f17 TC-Mini-4B-F16.gguf
32
+ e2c1a8a8b9a54e915a7138ecbc0c1590ea692e57350054d16d104c445417c6d1 TC-Mini-4B-Q4_K_M.gguf
33
+ a0833fd945174f78b37c2ff805df819a10bacdef70da280f525b6141f362c10e TC-Mini-4B-Q8_0.gguf
34
+ ```
35
+ License: Apache-2.0 (Qwen3).
TC-Mini-4B-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e91d02b780f1b071bc062d37d659a3c9ac6b90407b80ad8bfd15ac01b839f17
3
+ size 8051285120
TC-Mini-4B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c1a8a8b9a54e915a7138ecbc0c1590ea692e57350054d16d104c445417c6d1
3
+ size 2497280640
TC-Mini-4B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0833fd945174f78b37c2ff805df819a10bacdef70da280f525b6141f362c10e
3
+ size 4280405120