geoffmunn commited on
Commit
6428e96
·
verified ·
1 Parent(s): a2fb922

Rename Qwen3-Coder-30B-A3B-Instruct-Q6_K/README.md to Qwen3-Coder-30B-A3B-Instruct-f16-Q6_K/README.md

Browse files
{Qwen3-Coder-30B-A3B-Instruct-Q6_K → Qwen3-Coder-30B-A3B-Instruct-f16-Q6_K}/README.md RENAMED
@@ -3,6 +3,10 @@ license: apache-2.0
3
  tags:
4
  - gguf
5
  - qwen
 
 
 
 
6
  - llama.cpp
7
  - quantized
8
  - text-generation
@@ -14,7 +18,7 @@ base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
14
  author: geoffmunn
15
  ---
16
 
17
- # Qwen3-Coder-30B-A3B-Instruct:Q6_K
18
 
19
  Quantized version of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) at **Q6_K** level, derived from **f16** base weights.
20
 
@@ -28,11 +32,11 @@ Quantized version of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/
28
 
29
  ## Quality & Performance
30
 
31
- | Metric | Value |
32
- |-------|-------|
33
- | **Quality** | Near-FP16 |
34
- | **Speed** | 🐌 Slow |
35
- | **RAM Required** | ~37.5 GB |
36
  | **Recommendation** | Near-lossless. Minor gains. Use only if RAM allows. |
37
 
38
  ## Prompt Template (ChatML)
@@ -53,13 +57,13 @@ Set this in your app (LM Studio, OpenWebUI, etc.) for best results.
53
 
54
  Recommended defaults:
55
 
56
- | Parameter | Value |
57
- |---------|-------|
58
- | Temperature | 0.6 |
59
- | Top-P | 0.95 |
60
- | Top-K | 20 |
61
- | Min-P | 0.0 |
62
- | Repeat Penalty | 1.1 |
63
 
64
  Stop sequences: `<|im_end|>`, `<|im_start|>`
65
 
@@ -69,7 +73,7 @@ Here’s how you can query this model via API using `curl` and `jq`. Replace the
69
 
70
  ```bash
71
  curl http://localhost:11434/api/generate -s -N -d '{
72
- "model": "hf.co/geoffmunn/Qwen3-Coder-30B-A3B-Instruct:Q6_K",
73
  "prompt": "Respond exactly as follows: Explain how photosynthesis converts sunlight into chemical energy in plants.",
74
  "temperature": 0.5,
75
  "top_p": 0.95,
 
3
  tags:
4
  - gguf
5
  - qwen
6
+ - qwen3-coder
7
+ - qwen3-coder-30b-q6
8
+ - qwen3-coder-30b-q6_k
9
+ - qwen3-coder-30b-q6_k-gguf
10
  - llama.cpp
11
  - quantized
12
  - text-generation
 
18
  author: geoffmunn
19
  ---
20
 
21
+ # Qwen3-Coder-30B-A3B-Instruct-f16:Q6_K
22
 
23
  Quantized version of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) at **Q6_K** level, derived from **f16** base weights.
24
 
 
32
 
33
  ## Quality & Performance
34
 
35
+ | Metric | Value |
36
+ |--------------------|-----------------------------------------------------|
37
+ | **Quality** | Near-FP16 |
38
+ | **Speed** | 🐌 Slow |
39
+ | **RAM Required** | ~37.5 GB |
40
  | **Recommendation** | Near-lossless. Minor gains. Use only if RAM allows. |
41
 
42
  ## Prompt Template (ChatML)
 
57
 
58
  Recommended defaults:
59
 
60
+ | Parameter | Value |
61
+ |----------------|-------|
62
+ | Temperature | 0.6 |
63
+ | Top-P | 0.95 |
64
+ | Top-K | 20 |
65
+ | Min-P | 0.0 |
66
+ | Repeat Penalty | 1.1 |
67
 
68
  Stop sequences: `<|im_end|>`, `<|im_start|>`
69
 
 
73
 
74
  ```bash
75
  curl http://localhost:11434/api/generate -s -N -d '{
76
+ "model": "hf.co/geoffmunn/Qwen3-Coder-30B-A3B-Instruct-f16:Q6_K",
77
  "prompt": "Respond exactly as follows: Explain how photosynthesis converts sunlight into chemical energy in plants.",
78
  "temperature": 0.5,
79
  "top_p": 0.95,